• Publications
  • Influence
Bilateral Multi-Perspective Matching for Natural Language Sentences
TLDR
This work proposes a bilateral multi-perspective matching (BiMPM) model under the "matching-aggregation" framework that achieves the state-of-the-art performance on all tasks. Expand
Multi-Perspective Context Matching for Machine Comprehension
TLDR
A Multi-Perspective Context Matching (MPCM) model is proposed, which is an end-to-end system that directly predicts the answer beginning and ending points in a passage. Expand
Leveraging Context Information for Natural Question Generation
TLDR
This work proposes a model that matches the answer with the passage before generating the question and shows that this model outperforms the existing state of the art using rich features. Expand
Neural Cross-Lingual Entity Linking
TLDR
This paper proposes a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks and shows that this English-trained system can be applied, in zero-shot learning, to other languages by making surprisingly effective use of multi-lingual embeddings. Expand
Don’t Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing
TLDR
A unified architecture based on Sequence to Sequence models and Pointer Generator Network to handle both simple and complex queries is proposed and achieves state of the art performance on three publicly available datasets. Expand
A Unified Query-based Generative Model for Question Generation and Question Answering
TLDR
A query-based generative model for solving both tasks of question generation (QG) and question an- swering (QA), which follows the classic encoder- decoder framework and shows higher performance than the state-of-the-art baselines of the generative QA task. Expand
The IBM expressive text-to-speech synthesis system for American English
TLDR
A TTS engine which can be directed, via text markup, to use a variety of expressive styles, here, questioning, contrastive emphasis, and conveying good and bad news is described. Expand
Recent improvements to the IBM trainable speech synthesis system
TLDR
Through the combined data and algorithmic contributions, the current status of the trainable text-to-speech system at IBM is described, and the mean opinion score of the female voice is improved, from 3.68 to 4.68 and to 5.42. Expand
Current status of the IBM Trainable Speech Synthesis System
TLDR
The IBM Trainable Speech Synthesis System is a state-of-the-art, trainable, unit-selection based concatenative speech synthesiser that can operate both in general domain Text-to-Speech mode, and in Phrase Splicing mode to provide higher quality synthesis in limited domains. Expand
...
1
2
3
4
...