pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
Reasoning about implied relationships (e.g. paraphrastic, common sense, encyclopedic) between pairs of words is crucial for many cross-sentence inference problems. This paper proposes new methods for learning and using embeddings of word pairs that implicitly represent background knowledge about such relationships. Our pairwise embeddings are computed as a compositional function of each word’s representation, which is learned by maximizing the pointwise mutual information (PMI) with the contexts in which the the two words co-occur. We add these representations to the cross-sentence attention layer of existing inference models (e.g. BiDAF for QA, ESIM for NLI), instead of extending or replacing existing word embeddings. Experiments show a gain of 2.72% on the recently released SQuAD 2.0 and 1.3% on MultiNLI. Our representations also aid in better generalization with gains of around 6-7% on adversarial SQuAD datasets, and 8.8% on the adversarial entailment test set by Glockner et al.
Reasoning about implied relationships (e.g. paraphrastic, common sense, encyclopedic) between pairs of words is crucial for cross sentence inference problems such as question answering (QA) and natural language inference (NLI). In NLI, for example, given a premise such as “golf is prohibitively expensive”, inferring that the hypothesis “golf is a cheap pastime” is a contradiction requires one to know that expensive and cheap are antonyms. Recent work Glockner et al. (2018) has shown that current models, which rely heavily on unsupervised single-word embeddings, struggle to learn such relationships. In this paper, we show that they can be learned with word pair vectors (pair2vec), which are trained, unsupervised, at a very large scale, and which significantly improve performance when added to existing cross-sentence attention mechanisms.
|with X and Y baths|
|hot||cold||too X or too Y|
|neither X nor Y|
|in X, Y|
|Portland||Oregon||the X metropolitan area in Y|
|X International Airport in Y|
|food X are maize, Y, etc|
|crop||wheat||dry X, such as Y,|
|more X circles appeared in Y fields|
|X OS comes with Y play|
|Android||the X team at Y|
|X is developed by Y|
Unlike single-word representations, which are typically trained by modeling the co-occurrence of a target word with its context , our word-pair representations are learned by modeling the three-way co-occurrence between two words and the context that ties them together, as illustrated in Table 1. While similar training signals have been used to learn models for ontology construction Hearst (1992); Snow et al. (2005); Turney (2005); Shwartz et al. (2016) and knowledge base completion Riedel et al. (2013), this paper shows, for the first time, that large scale learning of pairwise embeddings can be used to directly improve the performance of neural cross-sentence inference models.
More specifically, we train a feedforward network that learns representations for the individual words and , as well as how to compose them into a pairwise embedding. Training is done by maximizing a generalized notion of the pointwise mutual information (PMI) among , , and their context using a variant of negative sampling Mikolov et al. (2013a); Levy and Goldberg (2014). Making a compositional function on individual word embeddings alleviates, at least partially, the sparsity that necessarily comes with embedding pairs of words, even at a very large scale.
We show that our embeddings can be added to existing cross-sentence inference models, such as BiDAF DocumentQA Seo et al. (2017); Clark and Gardner (2018) for QA and ESIM Chen et al. (2017) for NLI. Instead of changing the word embeddings that are fed into the encoder, we add the pretrained pair representations to higher layers in the network where cross sentence attention mechanisms are used. This allows the model to use the background knowledge that the pair embeddings implicitly encode to better reason about the likely relationships between the pairs of words it aligns to each other.
Experiments on varied cross-sentence inference tasks show strong gains over high-performing models, which already use contextualized ELMo embeddings Peters et al. (2018), by simply adding our word-pair embeddings with no other modifications – not even hyperparameter tuning. We show 2.72 F1 points over the BiDAF++ model Clark and Gardner (2018) on the SQuAD 2.0 QA benchmark Rajpurkar et al. (2018), as well as a 1.3 point gain over ESIM Chen et al. (2017) on MultiNLI Williams et al. (2018). Additionally, we show that our approach generalizes well to adversarial out-of-domain examples, with a 6-7% F1 increase on adversarial SQuAD Jia and Liang (2017) and a 8.8% gain on Glockner et al.’s 2018 NLI benchmark (both absolute). An analysis of pair2vec on word analogies suggests that it contains information complementary to single-word representations, and is particularly useful for encyclopedic and lexicographic relations.
2 Unsupervised Pretraining
Extending the distributional hypothesis to word pairs, we posit that similar word pairs tend to occur in similar contexts and that the contexts provide strong clues about the likely relationships that hold between the words (e.g. see Table 1). We assume a dataset of triplets, where each instance depicts a word pair and the context in which they appeared. W̄e learn two compositional representation functions, and , to encode the pair and the context, respectively, as -dimensional vectors (Section 2.1). The functions are trained using a variant of the negative sampling objective, which tries to embed word pairs close to the contexts with which they were observed (Section 2.2).
Our word-pair and context representations are both fixed-length vectors, composed from individual words. The word-pair representation function first embeds and normalizes the individual words with a shared lookup matrix :
These vectors, along with their element-wise product, are fed into a four-layer perceptron:
The context as a -dimensional vector using the function , which embeds each token with a lookup matrix , contextualizes it with a single-layer Bi-LSTM Hochreiter and Schmidhuber (1997), and then aggregates the entire context with attentive pooling:
where and . All parameters, including the lookup tables and , are trained.
Our representation is similar to two recently-proposed frameworks by Washio and Kato (2018a, b), but differs in that: (1) they use dependency paths as context, while we use surface form; (2) they encode the context as either a lookup table or the last state of a unidirectional LSTM. We also use a different objective, which we discuss next.
To optimize our compositional representation functions, we consider two variants of the negative sampling objective Mikolov et al. (2013a): bivariate and multivariate. The bivariate objective models the two-way distribution of context and (monolithic) word pair co-occurrences. We extend this to model the multivariate (three-way) distribution of word-word-context co-occurrences. We further augment the multivariate objective with typed sampling to adversarially generate additional negative examples. We discuss the impact of the bivariate and multivariate objectives (and other components) in Section 4.3.
Bivariate Negative Sampling
On one hand, our objective aspires to make and similar (i.e. have high inner products) for that were observed together in the data. At the same time, we wish to keep our pair vectors dis-similar from random context vectors. In a straightforward application of the original (bivariate) negative sampling objective, we could generate a negative example from each observed data instance by replacing the context with a randomly-sampled context :
where is the number of sampled contexts.
Assuming that the negative contexts are sampled from the empirical distribution – with being the portion of instances in the dataset – we can follow the proof in Levy and Goldberg (2014) to show that this objective converges into the pointwise mutual information (PMI) between the word pair and the context:
This objective primarily captures co-occurrences of word pairs and contexts. The modeling of co-occurences between target words, and themselves, is limited by the fact that the training data consists of word pairs that occur within a sentence. For better generalization to cross-sentence tasks, where the distribution of word pairs is different from that of the training data, we require a multivariate objective that captures the full three-way interaction between , , and .
Multivariate Negative Sampling
Here we depart from previous work, and in addition to negative sampling of contexts , we also introduce negative sampling of target words, and . Our ternary negative sampling objective, for each data instance, can be expressed as follows:
Our new objective also converges to a novel multivariate generalization of PMI, different from previous PMI extensions that were inspired by information theory Van de Cruys (2011) and heuristics Jameel et al. (2018).
where , the denominator, is:
i.e. a linear mixture of marginal probability products. By introducing terms such as and , the objective is essentially penalizing spurious correlations between one word and the context that disregard the other word. For instance, it would assign the pattern “X is a type of Y” a high score with (banana, fruit), but a lower score with (cat, fruit).
Though not necessary in our case, our objective can easily be extended to higher-order multivariate distributions by replacing every independently, which will likewise converge into a higher-order generalization of PMI.
In multivariate negative sampling, we typically replace and by sampling from their unigram distributions. In addition to this, we also sample uniformly from the top 100 words according to cosine similarity using distributional word vectors. The rationale for doing so is to encourage the model to learn relations between specific instances as opposed to more general types. For example, using California as a negative sample for Oregon helps the model to learn that the pattern “X is located in Y” fits the pair (Portland, Oregon), but not the pair (Portland, California). Similar adversarial constraints were used in knowledge base completion Toutanova et al. (2015) as well as word embeddings Li et al. (2017).
3 Adding pair2vec to Inference Models
We first present a general outline for incorporating pair2vec into attention-based architectures, and then discuss changes made to BiDAF++ and ESIM. The key idea is to inject our pairwise representations into the attention layer by reusing the cross-sentence attention weights. In addition to attentive pooling over single word representations, we also pool over cross-sentence word pair embeddings (Figure 1).
3.1 General Approach
We assume that we are given two sequences and . We represent the word-pair embeddings between and using the pretrained pair2vec model as:
We include embeddings in both directions, and , because the many relations can be expressed in both directions; e.g., hypernymy can be expressed via “X is a type of Y” as well as “Y such as X”. We take the normalization of each direction’s pair embedding because the heavy-tailed distribution of word pairs results in significant variance of their norms.
Let and be the vector representations of sequences and , as produced by the input encoder (e.g. ELMo embeddings contextualized with model-specific BiLSTMs). Furthermore, we assume that the base model computes soft word alignments between and via co-attention (5, 6), which are then used to compute -aware representations of :
The symmetric term is defined analogously. We refer to and as the inputs to the inference layer, since this layer computes some function over aligned word pairs, typically via a feedforward network and LSTMs. Seo et al. (2017); Peters et al. (2018); Chen et al. (2017). The inference layer is followed by an aggregation function (usually sum) and an output layer.
We conjecture that the inference layer effectively learns word-pair relationships from training data, and it should, therefore, help to augment its input with pair2vec. We augment (8) with the pair vectors (4) by concatenating a weighted average of the pair vectors involving , where the weights are the same computed via attention in (6):
The symmetric term is defined analogously.
3.2 Question Answering
We augment the inference layer in the BiDAF++ model with pair2vec. BiDAF++ is an improved version of the BiDAFNoAnswer Seo et al. (2017); Levy et al. (2017) which includes self-attention and ELMo embeddings from Peters et al. (2018). We found this variant to be stronger than the baselines presented in Rajpurkar et al. (2018) by over 2.5 F1. We use BiDAF++ as a baseline since its architecture is typical for QA systems, and, until recently, was state-of-the-art on SQuAD 2.0 and other benchmarks.
Let be the output of the passage encoder, and be the output of the question encoder.
In the later layers, is projected and recontextualized using a BiGRU. This is followed by self attention, and finally a prediction layer that predicts start and end tokens.
BiDAF++ with pair2vec
3.3 Natural Language Inference
Let be the output of the premise encoder, and be the output of the hypothesis encoder.
In the later layers, and are projected, recontextualized, and converted to a fixed-length vector for each sentence using multiple pooling schemes. These vectors are then passed on to an output layer, which predicts the class.
ESIM with pair2vec
The vector is augmented analogously.
For experiments on question-answering (Section 4.1) and natural language inference (Section 4.2), we use our full model which includes multivariate and typed negative sampling. We test other objectives and composition functions in Section 4.3
We use a January 2018 dump of Wikipedia, containing
96M sentences to train pair2vec. We restrict the vocabulary to the top 100K words based on frequency. During preprocessing, we remove all words in the corpus that aren’t in the vocabulary. We consider each word pair within a window of 5 in the preprocessed corpus, and subsample
For both word pairs and contexts, we use 300-dimensional word embeddings initialized with FastText Bojanowski et al. (2017). The context representation uses a single-layer Bi-LSTM with a hidden layer size of 100. We use 2 negative context samples and 3 negative argument samples for each pair-context tuple.
For pre-training, we used stochastic gradient descent with an initial learning rate of 0.01. We reduce the learning rate by a factor of 0.9 if the loss does not decrease for 300K steps. We use a batch size of 600, and train for 12 epochs.
For both end-task models, we use AllenNLP’s implementations Gardner et al. (2017) with default hyperparameters; we did not change any setting before or after injecting pair2vec. We use 0.15 dropout on our pretrained pair embeddings.
4.1 Question Answering
We experiment on the SQuAD 2.0 extractive question answering benchmark Rajpurkar et al. (2018), as well as the adversarially-created datasets of SQuAD 1.1 Rajpurkar et al. (2016); Jia and Liang (2017). Table 2 shows the performance of BiDAF++, with ELMo embeddings Peters et al. (2018), before and after adding pair2vec. Experiments on SQuAD 2.0 show that our pair representations improve performance by 2.72 F1. Moreover, adding pair2vec also results in better generalization on the adversarial SQuAD datasets with gains of 7.14 and 6.11 F1.
4.2 Natural Language Inference
|Models with GloVe|
|ESIM Chen et al. (2017)||77.0|
|KIM Chen et al. (2018)||87.7|
|ESIM + pair2vec||92.9|
|Models with ELMo|
|ESIM Peters et al. (2018)||84.6|
|ESIM + pair2vec||93.4|
We report the performance of our model on MultiNLI and the out-of-domain test set from Glockner et al. (2018) in Table 4. We outperform the ESIM + ELMo baseline by 1.3% on the matched as well as mismatched portions of the dataset.
We also record a gain of 8.8% absolute over ESIM on the Glockner et al. (2018) test set making our approach the state-of-the-art. Following the experimental setup in Glockner et al. (2018), we train all models on a combination of SNLI Bowman et al. (2015) and MultiNLI. Glockner et al. (2018) show that with the exception of KIM Chen et al. (2018), which uses WordNet features, several NLI models fail to generalize to this setting which involves lexical inference. For a fair comparison with KIM on the Glockner test set, we replace ELMo with GLoVE embeddings, and still outperform KIM by almost halving the error rate.
|Model||EM ()||F1 ()|
|pair2vec (Full Model)||69.20||72.68|
|Composition: 2 Layers||68.35 (-0.85)||71.65 (-1.03)|
|Composition: Multiply||67.10 (-2.20)||70.20 (-2.48)|
|Objective: Bivariate NS||68.63 (-0.57)||71.98 (-0.70)|
|Unsupervised: Pair Dist||67.07 (-2.13)||70.24 (-2.44)|
|No pair2vec (BiDAF)||66.66 (-2.54)||69.90 (-2.78)|
Ablating parts of pair2vec shows that all components of the model (Section 2) are useful. To show the importance of each component, we ablate it and report the EM and F1 on the development set of SQuAD 2.0 (Table 5). The full model, which uses a 4-layer MLP for and trains with multivariate negative sampling, achieves the highest F1 of 72.68.
We experiment with two alternative composition functions, a 2-layer MLP (Composition: 2 Layers) and element-wise multiplication (Composition: Multiply), which yield significantly smaller gains over the baseline BiDAF++ model. This result demonstrates the need for a deep and complicated composition function. By eliminating sampling of target words from the objective, we are also able to evaluate the bivariate negative sampling objective (Objective: Bivariate NS). Here we see a drop of 0.7 F1, accounting for about a quarter of the overall gain. This suggests that while the bulk of the signal is mined from the pair-context interactions, there is also valuable information in other interactions as well.
We also test whether specific pre-training of word pair representations is useful by replacing pair2vec embeddings with the vector offsets of pre-trained word embeddings (Unsupervised: Pair Dist). We follow the PairDistance method for word analogies Mikolov et al. (2013b), and represent the pair as the L2 normalized difference of single-word vectors: . We use the same FastText word vectors with which we initialized pair2vec before training. We observe a gain of only 0.34 F1 over the baseline, about 8 times smaller than the gains from the full pair2vec model.
|Relation||Context||X||Y (Top 3)|
|Antonymy/Exclusion||either X or Y||accept||reject, refuse, recognise|
|birth||death, fertility, arrival|
|hard||soft, brittle, polished|
|Hypernymy||including X and other Y||copper||ones, metals, mines|
|apps, browsers, searches|
|oak||oaks, hardwoods, elms|
|Hyponymy||X like Y||cities||solaris, speyer, medina|
|browsers||chrome, firefox, netscape|
|companies||bravo, nike, uber|
|Co-hyponymy||, X , Y ,||copper||malachite, flint, ivory|
|microsoft, bing, yahoo|
|oak||araucaria, hornbeam, blackjack|
|Meronymy||X is made of Y||cake||marzipan, icing, candles|
|statue||bronze, lenin, wax|
|utensils||copper, tea, brass|
|City-State||in X , Y .||portland||oregon, maine, dorset|
|dallas||tx, texas, va|
|oakland||california, ca, piedmont|
|City-City||from X to Y .||portland||salem, astoria, ogdensburg|
|dallas||denton, allatoona, addison|
|oakland||hayward, emeryville, berkeley|
|Profession||X , a famous Y ,||ronaldo||footballer, portuguese, player|
|monet||painter, painting, butterfly|
|orwell||writer, author, essay|
In Section 4 we showed that pair2vec adds additional information on top of single-word representations such as ELMo Peters et al. (2018). Here, we ask what this extra information is, and try to characterize which lexical relations are indeed better captured by pair2vec. To that end, we evaluate performance on a word analogy dataset with over 40 different relation types (Section 5.1), and observe how pair2vec fills hand-crafted relation patterns (Section 5.2).
5.1 Quantitative Analysis: Word Analogies
Word Analogy Dataset
Given a word pair and word , the word analogy task involves predicting a word such that . We use the Bigger Analogy Test Set (BATS) Gladkova et al. (2016) which contains four groups of relations: encyclopedic semantics (e.g., person-profession as in Einstein-physicist), lexicographic semantics (e.g., antonymy as in cheap-expensive), derivational morphology (e.g., noun forms as in oblige-obligation), and inflectional morphology (e.g., noun-plural as in bird-birds). Each group contains 10 sub-relations.
where , , , and represent FastText embeddings
Figure 2 shows how the accuracy on each category of relations varies with . For all four groups, adding pair2vec to 3CosAdd results in significant gains. In particular, the biggest relative improvements are observed for encyclopedic (356%) and lexicographic (51%) relations.
Table 6 shows the specific relations in which pair2vec made the largest absolute impact. The gains are particularly significant for relations where FastText embeddings provide limited signal. For example, the accuracy for substance meronyms goes from 3.8% to 14.5%. In some cases, there is also a synergistic effect; for instance, in noun+less, pair2vec alone scored 0% accuracy, but mixing it with 3CosAdd, which got 4.8% on its own, yielded 16% accuracy.
These results, alongside our experiments in Section 4, strongly suggest that pair2vec encodes information complementary to that in single-word embedding methods such as FastText and ELMo.
5.2 Qualitative Analysis: Slot Filling
To further explore how pair2vec encodes such complementary information, we consider a setting similar to that of knowledge base completion: given a Hearst-like context pattern and a single word , predict the other word from the entire vocabulary. We rank candidate words based on the scoring function in our training objective: . We use a fixed set of example relations and manually define their predictive context patterns and a small set of candidate words .
Table 7 shows the top three words. The model embeds correct pairs close to contexts predictive of the relation between them. For example, substituting Portland in the city-state pattern (“in X, Y .”), the top two words are Oregon and Maine, both US states with cities named Portland. When used with the city-city pattern (“from X to Y .”), the top two words are Salem and Astoria, both cities in Oregon. The word-context interaction often captures multiple relations; for example, Monet is used to refer to the painter (profession) as well as his paintings.
As intended, pair2vec captures the three-way interaction between word pairs and context, and not just the two-way interaction between a single word and its context (as in single-word embeddings). This profound difference allows pair2vec to complement single-word embeddings with additional information.
6 Related Work
Pretrained Word Embeddings
Many state-of-the-art models initialize their word representations using pretrained word embeddings such as word2vec Mikolov et al. (2013a) or ELMo Peters et al. (2018). These representations are typically trained using an interpretation of the Distributional Hypothesis Harris () in which the bivariate distribution of target words and contexts is modeled. Our work deviates from the word embedding literature in two major aspects. First, our goal is to represent pairs of words, not individual words. Second, our new PMI formulation models the trivariate distribution between the first word, the second word, and their joint context. Experiments show that our pair embeddings can complement individual word embeddings, and that they are perhaps capturing information that eludes the traditional interpretation of the Distributional Hypothesis.
Mining Textual Patterns
There is extensive literature on mining textual patterns to predict relations between words Hearst (1992); Snow et al. (2005); Turney (2005); Riedel et al. (2013); Toutanova et al. (2015); Shwartz and Dagan (2016). These approaches focus on relations between pairs of nouns (perhaps with the exception of VerbOcean Chklovski and Pantel (2004), which models relations between verbs). More recently, these approaches have been expanded to predict relations between unrestricted pairs of words Jameel et al. (2018); Espinosa Anke and Schockaert (2018), assuming that each word-pair was observed together during pretraining. Washio and Kato 2018a; 2018b relax this assumption with a compositional model that can represent any word pair, as long as each word appeared (individually) in the corpus.
These methods are evaluated on either intrinsic relation prediction tasks, such as BLESS Baroni and Lenci (2011) and CogALex Santus et al. (2016), or knowledge-base population benchmarks, e.g. FB15 Bordes et al. (2013). To the best of our knowledge, our work is the first to integrate pattern-based methods into modern high-performing semantic models and evaluate their impact on complex end-tasks like QA and NLI.
Integrating Knowledge in Complex Models
There has been some work on injecting external knowledge into NLP models. Ahn et al. (2016) integrate Freebase facts into a language model using a copying mechanism over fact attributes. Yang and Mitchell (2017) modify the LSTM cell to incorporate WordNet and NELL knowledge for event and entity extraction. For cross-sentence inference tasks, Weissenborn et al. (2018) and Mihaylov and Frank (2018) dynamically refine word representations by reading free text assertions from ConceptNet and Wikipedia abstracts. Our approach, on the other hand, relies on a relatively simple extension of existing cross-sentence inference models. Furthermore, we do not need to dynamically retrieve and process knowledge base facts or Wikipedia texts, and just pretrain our pair vectors in advance.
Perhaps the most similar approach to ours is KIM Chen et al. (2017), which integrates word-pair vectors into the ESIM model for NLI in a very similar way to ours. However, KIM’s word-pair vectors contain only hand-engineered word-relation indicators from WordNet, whereas our word-pair vectors are automatically learned from unlabeled text. Our vectors can therefore reflect relation types that do not exist in WordNet (such as profession) as well as word pairs that do not have a direct link in WordNet (e.g. bronze and statue); see Table 7 for additional examples.
We presented new methods for learning and using embeddings of word pairs that implicitly represent background knowledge. Our pairwise embeddings are computed as a compositional function of representations of the individual words, which is learned by maximizing a variant of the pointwise mutual information (PMI) with the contexts in which the the two words co-occur. Experiments on benchmark cross-sentence inference datasets demonstrated that adding these representations to existing models results in sizable improvements for both in-domain and adversarial settings.
Appendix A Multivariate Negative Sampling
In this appendix, we elaborate on mathematical details of multivariate negative sampling to support our claims in Section 2.2.
a.1 Global Objective
Equation (2.2) in Section 2.2 characterizes the local objective for each data instance. To understand the mathematical properties of this objective, we must first describe the global objective in terms of the entire dataset. However, this cannot be done by simply summing the local objective for each , since each such example may appear multiple times in our dataset. Moreover, due to the nature of negative sampling, the number of times an triplet appears as a positive example will almost always be different from the number of times it appears as a negative one. Therefore, we must determine the frequency in which each triplet appears in each role.
We first denote the number of times the example appears in the dataset as ; this is also the number of times is used as a positive example. We observe that the expected number of times is used as a corrupt example is , since can only be created as a corrupt example by randomly sampling from an example that already contained and . The number of times is used as a corrupt or example can be derived analogously. Therefore, the global objective of our trenary negative sampling approach is:
a.2 Relation to Multivariate PMI
With the global objective, we can now ask what is the optimal value of (21) by comparing the partial derivative of (18) to zero. This derivative is in fact equal to the partial derivative of (19), since it is the only component of the global objective in which appears:
The partial derivative of (19) can be expressed as:
which can be reformulated as:
By expanding the fraction by (i.e. dividing by the size of the dataset), we essentially convert all the frequency counts (e.g. ) to empirical probabilities (e.g. ), and arrive at Equation (2) in Section 2.2.
a.3 Other Multivariate PMI Formulations
Previous work has proposed different multivariate formulations of PMI, shown in Table 8. Van de Cruys (2011) presented specific interaction information () and specific correlation (). In addition to those metrics, Jameel et al. (2018) experimented with , which is the bivariate PMI between and , and with . Our formulation deviates from previous work, and, to the best of our knowledge, cannot be trivially expressed by one of the existing metrics.
- The global objective over the entire dataset is more complicated; we present it in Appendix A.1.
- See Appendix A.3 for exact formulations.
- A full proof is provided in Appendix A.2.
- Applying typed sampling also changes the value to which our objective will converge, and will replace the unigram probabilities in Equation (3) to reflect the type-based distribution.
- The passage is typically denoted and the question , but we use for passage and for question for consistency with our general notation.
- The premise is typically denoted and the hypothesis , but we use for premise and for hypothesis for consistency with our general notation.
- Like in word2vec, subsampling reduces the size of the training dataset and speeds up training. We define the word pair probability as the multiplication of unigram probabilities of individual words in the pair.
- On Titan X GPUs, the training takes about a week.
- The FastText embeddings in the analysis were retrained using the same Wikipedia corpus used to train pair2vec to control for the corpus when comparing the two methods.
- Sungjin Ahn, Heeyoul Choi, Tanel Pärnamaa, and Yoshua Bengio. 2016. A neural knowledge language model. CoRR.
- Marco Baroni and Alessandro Lenci. 2011. How we blessed distributional semantic evaluation. In Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics, GEMS ’11, pages 1–10, Stroudsburg, PA, USA. Association for Computational Linguistics.
- Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146.
- Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 26, pages 2787–2795. Curran Associates, Inc.
- Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642. Association for Computational Linguistics.
- Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen, and Si Wei. 2018. Neural natural language inference models enhanced with external knowledge. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2406–2417. Association for Computational Linguistics.
- Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, and Diana Inkpen. 2017. Enhanced lstm for natural language inference. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1657–1668. Association for Computational Linguistics.
- Timothy Chklovski and Patrick Pantel. 2004. Verbocean: Mining the web for fine-grained semantic verb relations. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing.
- Christopher Clark and Matt Gardner. 2018. Simple and effective multi-paragraph reading comprehension. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 845–855. Association for Computational Linguistics.
- Tim Van de Cruys. 2011. Two multivariate generalizations of pointwise mutual information. In Proceedings of the Workshop on Distributional Semantics and Compositionality, pages 16–20. Association for Computational Linguistics.
- Luis Espinosa Anke and Steven Schockaert. 2018. Seven: Augmenting word embeddings with unsupervised relation vectors. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2653–2665. Association for Computational Linguistics.
- Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke S. Zettlemoyer. 2017. Allennlp: A deep semantic natural language processing platform.
- Anna Gladkova, Aleksandr Drozd, and Satoshi Matsuoka. 2016. Analogy-based detection of morphological and semantic relations with word embeddings: What works and what doesn’t. In Proceedings of the NAACL-HLT SRW, pages 47–54, San Diego, California, June 12-17, 2016. ACL.
- Max Glockner, Vered Shwartz, and Yoav Goldberg. 2018. Breaking nli systems with sentences that require simple lexical inferences. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 650–655. Association for Computational Linguistics.
- Zellig Harris. 1954. Distributional structure. Word, 10(23):146–162.
- Marti Hearst. 1992. Automatic acquisition of hyponyms from large text corpora. In Proceedings of the 14th International Conference on Computational Linguistics, Nantes, France.
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput., 9(8):1735–1780.
- Shoaib Jameel, Zied Bouraoui, and Steven Schockaert. 2018. Unsupervised learning of distributional relation vectors. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 23–33. Association for Computational Linguistics.
- Robin Jia and Percy Liang. 2017. Adversarial examples for evaluating reading comprehension systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2021–2031. Association for Computational Linguistics.
- Omer Levy, Ido Dagan, and Jacob Goldberger. 2014. Focused entailment graphs for open ie propositions. In Proceedings of the Eighteenth Conference on Computational Natural Language Learning, pages 87–97. Association for Computational Linguistics.
- Omer Levy and Yoav Goldberg. 2014. Neural word embedding as implicit matrix factorization. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS’14, pages 2177–2185, Cambridge, MA, USA. MIT Press.
- Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-shot relation extraction via reading comprehension. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), Vancouver, Canada, August 3-4, 2017, pages 333–342.
- Bofang Li, Tao Liu, Zhe Zhao, Buzhou Tang, Aleksandr Drozd, Anna Rogers, and Xiaoyong Du. 2017. Investigating different syntactic context types and context representations for learning word embeddings. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2421–2431. Association for Computational Linguistics.
- Todor Mihaylov and Anette Frank. 2018. Knowledgeable reader: Enhancing cloze-style reading comprehension with external commonsense knowledge. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 821–832. Association for Computational Linguistics.
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013a. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States., pages 3111–3119.
- Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013b. Linguistic regularities in continuous space word representations. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 746–751. Association for Computational Linguistics.
- Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227–2237. Association for Computational Linguistics.
- Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don’t know: Unanswerable questions for squad. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 784–789. Association for Computational Linguistics.
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics.
- Sebastian Riedel, Limin Yao, Benjamin M. Marlin, and Andrew McCallum. 2013. Relation extraction with matrix factorization and universal schemas. In Joint Human Language Technology Conference/Annual Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL).
- Enrico Santus, Anna Gladkova, Stefan Evert, and Alessandro Lenci. 2016. The cogalex-v shared task on the corpus-based identification of semantic relations. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V), pages 69–79. The COLING 2016 Organizing Committee.
- Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2017. Bidirectional attention flow for machine comprehension. In Proceedings of the International Conference on Learning Representations (ICLR).
- Vered Shwartz and Ido Dagan. 2016. Path-based vs. distributional information in recognizing lexical semantic relations. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon, CogALex@COLING 2016, Osaka, Japan, December 12, 2016, pages 24–29.
- Vered Shwartz, Yoav Goldberg, and Ido Dagan. 2016. Improving hypernymy detection with an integrated path-based and distributional method. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2389–2398. Association for Computational Linguistics.
- Rion Snow, Daniel Jurafsky, and Andrew Y. Ng. 2005. Learning syntactic patterns for automatic hypernym discovery. In L. K. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems 17, pages 1297–1304. MIT Press.
- Kristina Toutanova, Danqi Chen, Patrick Pantel, Hoifung Poon, Pallavi Choudhury, and Michael Gamon. 2015. Representing text for joint embedding of text and knowledge bases. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pages 1499–1509.
- Peter D. Turney. 2005. Measuring semantic similarity by latent relational analysis. In Proceedings of the 19th International Joint Conference on Artificial Intelligence, IJCAI’05, pages 1136–1141, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
- Koki Washio and Tsuneaki Kato. 2018a. Filling missing paths: Modeling co-occurrences of word pairs and dependency paths for recognizing lexical semantic relations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1123–1133. Association for Computational Linguistics.
- Koki Washio and Tsuneaki Kato. 2018b. Neural latent relational analysis to capture lexical semantic relations in a vector space. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. Association for Computational Linguistics.
- Dirk Weissenborn, Tomas Kocisky, and Chris Dyer. 2018. Dynamic integration of background knowledge in neural nlu systems. CoRR.
- Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122. Association for Computational Linguistics.
- Bishan Yang and Tom Mitchell. 2017. Leveraging knowledge bases in lstms for improving machine reading. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1436–1446. Association for Computational Linguistics.