TACL 2018

Generating Sentences by Editing Prototypes

TACL 2018 kelvinguu/neural-editor

We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence.

LANGUAGE MODELLING

Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns

TACL 2018 google-research-datasets/gap-coreference

Coreference resolution is an important task for natural language understanding, and the resolution of ambiguous pronouns a longstanding challenge.

COREFERENCE RESOLUTION

Learning Structured Text Representations

TACL 2018 nlpyang/structured

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations.

Do latent tree learning models identify meaningful structure in sentences?

TACL 2018 NYU-MLL/spinn

Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-truth parse trees at training time.

SENTENCE CLASSIFICATION

Representation Learning for Grounded Spatial Reasoning

TACL 2018 JannerM/spatial-reasoning

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment.

REPRESENTATION LEARNING

Linear Algebraic Structure of Word Senses, with Applications to Polysemy

TACL 2018 PrincetonML/SemanticVector

A novel aspect of our technique is that each extracted word sense is accompanied by one of about 2000 "discourse atoms" that gives a succinct description of which other words co-occur with that word sense.

INFORMATION RETRIEVAL WORD EMBEDDINGS

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

TACL 2018 ccsasuke/adan

To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exists.

CROSS-LINGUAL DOCUMENT CLASSIFICATION CROSS-LINGUAL TRANSFER SENTIMENT ANALYSIS

Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis

TACL 2018 stangelid/milnet-sent

We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL).

MULTIPLE INSTANCE LEARNING SENTIMENT ANALYSIS

Universal Word Segmentation: Implementation and Interpretation

TACL 2018 yanshao9798/segmenter

Word segmentation is a low-level NLP task that is non-trivial for a considerable number of languages.

Low-Rank RNN Adaptation for Context-Aware Language Modeling

TACL 2018 ajaech/calm

A context-aware language model uses location, user and/or domain metadata (context) to adapt its predictions.

LANGUAGE MODELLING