HLT 2018

Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model

HLT 2018 tensorflow/models

Automatic interpretation of the relation between the constituents of a noun compound, e. g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications.

Self-Attention with Relative Position Representations

HLT 2018 tensorflow/tensor2tensor

On the WMT 2014 English-to-German and English-to-French translation tasks, this approach yields improvements of 1. 3 BLEU and 0. 3 BLEU over absolute position representations, respectively.

MACHINE TRANSLATION

Classical Structured Prediction Losses for Sequence to Sequence Learning

HLT 2018 pytorch/fairseq

There has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam.

ABSTRACTIVE TEXT SUMMARIZATION MACHINE TRANSLATION STRUCTURED PREDICTION

Unsupervised Keyphrase Extraction with Multipartite Graphs

HLT 2018 boudinfl/pke

We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure.

A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications

HLT 2018 allenai/PeerRead

In the first task, we show that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.

Character-based Neural Networks for Sentence Pair Modeling

HLT 2018 lanwuwei/SPM_toolkit

Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference.

NATURAL LANGUAGE INFERENCE PARAPHRASE IDENTIFICATION SEMANTIC TEXTUAL SIMILARITY SENTENCE PAIR MODELING

Ranking Sentences for Extractive Summarization with Reinforcement Learning

HLT 2018 shashiongithub/Refresh

In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective.

DOCUMENT SUMMARIZATION

A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference

HLT 2018 nyu-mll/multiNLI

This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding.

DOMAIN ADAPTATION NATURAL LANGUAGE INFERENCE

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

HLT 2018 cai-lw/KBGAN

This framework is independent of the concrete form of generator and discriminator, and therefore can utilize a wide variety of knowledge graph embedding models as its building blocks.

KNOWLEDGE BASE COMPLETION KNOWLEDGE GRAPH EMBEDDING KNOWLEDGE GRAPH EMBEDDINGS KNOWLEDGE GRAPHS LINK PREDICTION

Mittens: An Extension of GloVe for Learning Domain-Specialized Representations

HLT 2018 roamanalytics/mittens

We present a simple extension of the GloVe representation learning model that begins with general-purpose representations and updates them based on data from a specialized domain.

REPRESENTATION LEARNING