Proceedings ArticleDOI
Learning question classifiers
TLDR
A hierarchical classifier is learned that is guided by a layered semantic hierarchy of answer types, and eventually classifies questions into fine-grained classes.Abstract:
In order to respond correctly to a free form factual question given a large collection of texts, one needs to understand the question to a level that allows determining some of the constraints the question imposes on a possible answer. These constraints may include a semantic classification of the sought after answer and may even suggest using different strategies when looking for and verifying a candidate answer.This paper presents a machine learning approach to question classification. We learn a hierarchical classifier that is guided by a layered semantic hierarchy of answer types, and eventually classifies questions into fine-grained classes. We show accurate results on a large collection of free-form questions used in TREC 10.read more
Citations
More filters
Proceedings ArticleDOI
Convolutional Neural Networks for Sentence Classification
TL;DR: The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
Posted Content
Convolutional Neural Networks for Sentence Classification
TL;DR: In this article, CNNs are trained on top of pre-trained word vectors for sentence-level classification tasks and a simple CNN with little hyperparameter tuning and static vectors achieves excellent results on multiple benchmarks.
Posted Content
Representation Learning with Contrastive Predictive Coding
TL;DR: This work proposes a universal unsupervised learning approach to extract useful representations from high-dimensional data, which it calls Contrastive Predictive Coding, and demonstrates that the approach is able to learn useful representations achieving strong performance on four distinct domains: speech, images, text and reinforcement learning in 3D environments.
Proceedings ArticleDOI
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Nils Reimers,Iryna Gurevych +1 more
TL;DR: Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity is presented.
Proceedings ArticleDOI
A Convolutional Neural Network for Modelling Sentences
TL;DR: A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
References
More filters
Book ChapterDOI
Parsing By Chunks
TL;DR: The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
Proceedings Article
FALCON: Boosting Knowledge for Answer Engines
Sanda M. Harabagiu,Dan Moldovan,Marius Pasca,Rada Mihalcea,Mihai Surdeanu,Razvan Bunescu,Corina R. Gîrju,Vasile Rus,Paul Morarescu +8 more
TL;DR: FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance is discussed.
Journal ArticleDOI
A Winnow-Based Approach to Context-Sensitive Spelling Correction
Andrew R. Golding,Dan Roth +1 more
TL;DR: This work presents an algorithm combining variants of Winnow and weighted-majority voting, and applies it to a problem in the aforementioned class: context-sensitive spelling correction, and finds that WinSpell achieves accuracies significantly higher than BaySpell was able to achieve in either the pruned or unpruned condition.
Posted Content
A Winnow-Based Approach to Context-Sensitive Spelling Correction
Andrew R. Golding,Dan Roth +1 more
TL;DR: The authors presented an algorithm combining variants of Winnow and weighted-majority voting, and applied it to a problem in the aforementioned class: context-sensitive spelling correction, which is the task of fixing spelling errors that happen to result in valid words, such as substituting "to" for "too", "casual" for 'causal", etc.
Proceedings ArticleDOI
Deep Read: A Reading Comprehension System
TL;DR: Initial work on Deep Read, an automated reading comprehension system that accepts arbitrary text input (a story) and answers questions about it is described, with a baseline system that retrieves the sentence containing the answer 30--40% of the time.