We propose a new neural model for word embeddings, which uses Unitary Matrices as the primary device for encoding lexical information. It uses simple matrix multiplication to derive matrices for large units, yielding a sentence processing model that is strictly compositional, does not lose information over time steps, and is transparent, in the sense that word embeddings can be analysed regardless of context. This model does not employ activation functions, and so the network is fully accessible to analysis by the methods of linear algebra at each point in its operation on an input sequence. We test it in two NLP agreement tasks and obtain rule like perfect accuracy, with greater stability than current state-of-the-art systems. Our proposed model goes some way towards offering a class of computationally powerful deep learning systems that can be fully understood and compared to human cognitive processes for natural language learning and representation.

We study the influence of context on sentence acceptability. First we compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Moreover, in relevant contexts we observe a discourse coherence effect that uniformly raises acceptability. Next, we test unidirectional and bidirectional language models in their ability to predict acceptability ratings. The bidirectional models show very promising results, with the best model achieving a new state-of-the-art for unsupervised acceptability prediction. The two sets of experiments provide insights into the cognitive aspects of sentence processing and central issues in the computational modeling of text and discourse.

We present BIS, a Bayesian Inference Semantics, for probabilistic reasoning in natural language. The current system is based on the framework of Bernardy et al. (2018), but departs from it in important respects. BIS makes use of Bayesian learning for inferring a hypothesis from premises. This involves estimating the probability of the hypothesis, given the data supplied by the premises of an argument. It uses a syntactic parser to generate typed syntactic structures that serve as input to a model generation system. Sentences are interpreted compositionally to probabilistic programs, and the corresponding truth values are estimated using sampling methods. BIS successfully deals with various probabilistic semantic phenomena, including frequency adverbs, generalised quantifiers, generics, and vague predicates. It performs well on a number of interesting probabilistic reasoning tasks. It also sustains most classically valid inferences (instantiation, de Morgan’s laws, etc.). To test BIS we have built an experimental test suite with examples of a range of probabilistic and classical inference patterns.

We conduct two experiments to study the effect of context on metaphor paraphrase aptness judgments. The first is an AMT crowd source task in which speakers rank metaphor-paraphrase candidate sentence pairs in short document contexts for paraphrase aptness. In the second we train a composite DNN to predict these human judgments, first in binary classifier mode, and then as gradient ratings. We found that for both mean human judgments and our DNN’s predictions, adding document context compresses the aptness scores towards the center of the scale, raising low out-of-context ratings and decreasing high out-of-context scores. We offer a provisional explanation for this compression effect.

In this paper, we investigate the effect of enhancing lexical embeddings in LSTM language models (LM) with syntactic and semantic representations. We evaluate the language models using perplexity, and we evaluate the performance of the models on the task of predicting human sentence acceptability judgments. We train LSTM language models on sentences automatically annotated with universal syntactic dependency roles (Nivre, 2016), dependency depth and universal semantic tags (Abzianidze et al., 2017) to predict sentence acceptability judgments. Our experiments indicate that syntactic tags lower perplexity, while semantic tags increase it. Our experiments also show that neither syntactic nor semantic tags improve the performance of LSTM language models on the task of predicting sentence acceptability judgments.

In this paper, we present a Bayesian approach to natural language semantics. Our main focus is on the inference task in an environment where judgments require probabilistic reasoning. We treat nouns, verbs, adjectives, etc. as unary predicates, and we model them as boxes in a bounded domain. We apply Bayesian learning to satisfy constraints expressed as premises. In this way we construct a model, by specifying boxes for the predicates. The probability of the hypothesis (the conclusion) is evaluated against the model that incorporates the premises as constraints.

We investigate the influence that document context exerts on human acceptability judgements for English sentences, via two sets of experiments. The first compares ratings for sentences presented on their own with ratings for the same set of sentences given in their document contexts. The second assesses the accuracy with which two types of neural models — one that incorporates context during training and one that does not — predict these judgements. Our results indicate that: (1) context improves acceptability ratings for ill-formed sentences, but also reduces them for well-formed sentences; and (2) context helps unsupervised systems to model acceptability.

We propose a new annotated corpus for metaphor interpretation by paraphrase, and a novel DNN model for performing this task. Our corpus consists of 200 sets of 5 sentences, with each set containing one reference metaphorical sentence, and four ranked candidate paraphrases. Our model is trained for a binary classification of paraphrase candidates, and then used to predict graded paraphrase acceptability. It reaches an encouraging 75% accuracy on the binary classification task, and high Pearson (.75) and Spearman (.68) correlations on the gradient judgment prediction task.

We propose a compositional Bayesian semantics that interprets declarative sentences in a natural language by assigning them probability conditions. These are conditional probabilities that estimate the likelihood that a competent speaker would endorse an assertion, given certain hypotheses. Our semantics is implemented in a functional programming language. It estimates the marginal probability of a sentence through Markov Chain Monte Carlo (MCMC) sampling of objects in vector space models satisfying specified hypotheses. We apply our semantics to examples with several predicates and generalised quantifiers, including higher-order quantifiers. It captures the vagueness of predication (both gradable and non-gradable), without positing a precise boundary for classifier application. We present a basic account of semantic learning based on our semantic system. We compare our proposal to other current theories of probabilistic semantics, and we show that it offers several important advantages over these accounts.

We consider the extent to which different deep neural network (DNN) configurations can learn syntactic relations, by taking up Linzen et al.’s (2016) work on subject-verb agreement with LSTM RNNs. We test their methods on a much larger corpus than they used (a ⇠24 million example part of the WaCky corpus, instead of their ⇠1.35 million example corpus, both drawn from Wikipedia). We experiment with several different DNN architectures (LSTM RNNs, GRUs, and CNNs), and alternative parameter settings for these systems (vocabulary size, training to test ratio, number of layers, memory size, drop out rate, and lexical embedding dimension size). We also try out our own unsupervised DNN language model. Our results are broadly compatible with those that Linzen et al. report. However, we discovered some interesting, and in some cases, surprising features of DNNs and language models in their performance of the agreement learning task. In particular, we found that DNNs require large vocabularies to form substantive lexical embeddings in order to learn structural patterns. This finding has interesting consequences for our understanding of the way in which DNNs represent syntactic information. It suggests that DNNs learn syntactic patterns more efficiently through rich lexical embeddings, with semantic as well as syntactic cues, than from training on lexically impoverished strings that highlight structural patterns.

Type theory has played an important role in specifying the formal connection between syntactic structure and semantic interpretation within the history of formal semantics. In recent years rich type theories developed for the semantics of programming languages have become influential in the semantics of natural language. The use of probabilistic reasoning to model human learning and cognition has become an increasingly important part of cognitive science. In this paper we offer a probabilistic formulation of a rich type theory, Type Theory with Records (TTR), and we illustrate how this framework can be used to approach the problem of semantic learning. Our probabilistic version of TTR is intended to provide an interface between the cognitive process of classifying situations according to the types that they instantiate, and the compositional semantics of natural language.

Classical intensional semantic frameworks, like Montague’s Intensional Logic (IL), identify intensional identity with logical equivalence. This criterion of co-intensionality is excessively coarse-grained, and it gives rise to several well-known difficulties. Theories of fine-grained intensionality have been been proposed to avoid this problem. Several of these provide a formal solution to the problem, but they do not ground this solution in a substantive account of intensional difference. Applying the distinction between operational and denotational meaning, developed for the semantics of programming languages, to the interpretation of natural language expressions, offers the basis for such an account. It permits us to escape some of the complications generated by the traditional modal characterization of intensions.