Related papers: Decomposing Generalization: Models of Generic, Hab…

Distributed word embeddings have shown superior performances in numerous Natural Language Processing (NLP) tasks. However, their performances vary significantly across different tasks, implying that the word embeddings learnt by those…

We analyze the ability of pre-trained language models to transfer knowledge among datasets annotated with different type systems and to generalize beyond the domain and dataset they were trained on. We create a meta task, over multiple…

Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is…

Creating a descriptive grammar of a language is an indispensable step for language documentation and preservation. However, at the same time it is a tedious, time-consuming task. In this paper, we take steps towards automating this process…

In this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to document indicators…

Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we…

With the wide adoption of black-box models, instance-based \emph{post hoc} explanation tools, such as LIME and SHAP became increasingly popular. These tools produce explanations, pinpointing contributions of key features associated with a…

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of…

We present a framework for uncovering and exploiting dependencies among tools and documents to enhance exemplar artifact generation. Our method begins by constructing a tool knowledge graph from tool schemas,including descriptions,…

Conventional phrase grounding aims to localize noun phrases mentioned in a given caption to their corresponding image regions, which has achieved great success recently. Apparently, sole noun phrase grounding is not enough for cross-modal…

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how…

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized…

Word embeddings are a powerful approach for capturing semantic similarity among terms in a vocabulary. In this paper, we develop exponential family embeddings, a class of methods that extends the idea of word embeddings to other types of…

We investigate neural models' ability to capture lexicosyntactic inferences: inferences triggered by the interaction of lexical and syntactic information. We take the task of event factuality prediction as a case study and build a…

Statistical ensembles of networks, i.e., probability spaces of all networks that are consistent with given aggregate statistics, have become instrumental in the analysis of complex networks. Their numerical and analytical study provides the…

Sequence-to-sequence (seq2seq) models are prevalent in semantic parsing, but have been found to struggle at out-of-distribution compositional generalization. While specialized model architectures and pre-training of seq2seq models have been…

Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

In this work, we leverage the linear algebraic structure of distributed word representations to automatically extend knowledge bases and allow a machine to learn new facts about the world. Our goal is to extract structured facts from…