CONLL 2017

Making Neural QA as Simple as Possible but not Simpler

CONLL 2017 uclmr/jack

We argue that this surprising finding puts results of previous systems and the complexity of recent QA datasets into perspective.

QUESTION ANSWERING READING COMPREHENSION

Learning What is Essential in Questions

CONLL 2017 allenai/essential-terms

Question answering (QA) systems are easily distracted by irrelevant or redundant words in questions, especially when faced with long or multi-sentence questions in difficult domains.

INFORMATION RETRIEVAL QUESTION ANSWERING SEMANTIC PARSING

Neural Structural Correspondence Learning for Domain Adaptation

CONLL 2017 yftah89/Neural-SCLDomain-Adaptation

Particularly, our model is a three-layer neural network that learns to encode the nonpivot features of an input example into a low-dimensional representation, so that the existence of pivot features (features that are prominent in both domains and convey useful information for the NLP task) in the example can be decoded from that representation.

DENOISING DOMAIN ADAPTATION SENTIMENT ANALYSIS WORD EMBEDDINGS

A phoneme clustering algorithm based on the obligatory contour principle

CONLL 2017 cvocp/cvocp

This paper explores a divisive hierarchical clustering algorithm based on the well-known Obligatory Contour Principle in phonology.

Encoding of phonology in a recurrent neural model of grounded speech

CONLL 2017 gchrupala/encoding-of-phonology

We study the representation and encoding of phonemes in a recurrent neural network model of grounded speech.

Zero-Shot Relation Extraction via Reading Comprehension

CONLL 2017 zhuzhicai/SQuAD2.0-Baseline-Test-with-BiDAF-No-Answer

We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot.

READING COMPREHENSION RELATION EXTRACTION SLOT FILLING ZERO-SHOT LEARNING

A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

CONLL 2017 jungokasai/stagging_srl

However, when automatically predicted part-of-speech tags are provided as input, it substantially outperforms all previous local models and approaches the best reported results on the English CoNLL-2009 dataset.

SEMANTIC ROLE LABELING