Related papers: Paraphrase-Supervised Models of Compositionality

We investigate two specific manifestations of compositionality in Neural Machine Translation (NMT) : (1) Productivity - the ability of the model to extend its predictions beyond the observed length in training data and (2) Systematicity -…

Sequence-to-sequence models excel at handling natural language variation, but have been shown to struggle with out-of-distribution compositional generalization. This has motivated new specialized architectures with stronger compositional…

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind.…

We present a factorized compositional distributional semantics model for the representation of transitive verb constructions. Our model first produces (subject, verb) and (verb, object) vector representations based on the similarity of the…

Identifying the relations that exist between words (or entities) is important for various natural language processing tasks such as, relational search, noun-modifier classification and analogy detection. A popular approach to represent the…

We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based…

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations…

Supervised topic models are often sought to balance prediction quality and interpretability. However, when models are (inevitably) misspecified, standard approaches rarely deliver on both. We introduce a novel approach, the…

Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. Do the necessary…

Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled…

We present PaRTE, a collection of 1,126 pairs of Recognizing Textual Entailment (RTE) examples to evaluate whether models are robust to paraphrasing. We posit that if RTE models understand language, their predictions should be consistent…

A significant amount of information in today's world is stored in structured and semi-structured knowledge bases. Efficient and simple methods to query them are essential and must not be restricted to only those who have expertise in formal…

Many structured prediction problems (particularly in vision and language domains) are ambiguous, with multiple outputs being correct for an input - e.g. there are many ways of describing an image, multiple ways of translating a sentence;…

We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free" -- by creating it from data that is already available rather than having to create more…

Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised…

Despite the recent success of contextualized language models on various NLP tasks, language model itself cannot capture textual coherence of a long, multi-sentence document (e.g., a paragraph). Humans often make structural decisions on what…

Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However,…

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…

The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sentences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We introduce both a…

Language models are often used as the backbone of modern dialogue systems. These models are pre-trained on large amounts of written fluent language. Repetition is typically penalised when evaluating language model generations. However, it…