Search Results for author:
Found 51 papers, 15 papers with code
Findings of the 2021 Conference on Machine Translation (WMT21)
This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021. In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories.
Which Words Matter in Defining Phrase Reordering Behavior in Statistical Machine Translation?
Lexicalized and hierarchical reordering models use relative frequencies of fully lexicalized phrase pairs to learn phrase reordering distributions.
NLQuAD: A Non-Factoid Long Question Answering Data Set
We introduce NLQuAD, the first data set with baseline methods for non-factoid long question answering, a task requiring document-level language understanding.
Findings of the 2020 Conference on Machine Translation (WMT20)
In the news task, participants were asked to build machine translation systems for any of 11 language pairs, to be evaluated on test sets consisting mainly of news stories.
Optimizing Transformer for Low-Resource Neural Machine Translation
Language pairs with limited amounts of parallel data, also known as low-resource languages, remain a challenge for neural machine translation.
The Unreasonable Volatility of Neural Machine Translation Models
Recent works have shown that Neural Machine Translation (NMT) models achieve impressive performance, however, questions about understanding the behavior of these models remain unanswered.
Conversations with Search Engines: SERP-based Conversational Response Generation
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner.
TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
We hypothesize that the deeper reason is that in the training corpora, there are hard tokens that are more difficult for a generative model to learn than others and, once learning has finished, hard tokens are still under-learned, so that repetitive generations are more likely to happen.
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions.
BERT for Evidence Retrieval and Claim Verification
Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge.
Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
Given a conversational context and background knowledge, we first learn a topic transition vector to encode the most likely text fragments to be used in the next response, which is then used to guide the local KS at each decoding timestamp.
RefNet: A Reference-aware Network for Background Based Conversation
In this paper, we propose a Reference-aware Network (RefNet) to address the two issues.
Findings of the 2019 Conference on Machine Translation (WMT19)
This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019.
An Intrinsic Nearest Neighbor Analysis of Neural Machine Translation Architectures
We compare transformer and recurrent models in a more intrinsic way in terms of capturing lexical semantics and syntactic structures, in contrast to extrinsic approaches used by previous works.
Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss
Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses.
Findings of the 2018 Conference on Machine Translation (WMT18)
This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2018.
Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation
In this work, we explore different aspects of back-translation, and show that words with high prediction loss during training benefit most from the addition of synthetic data.
The Importance of Being Recurrent for Modeling Hierarchical Structure
Recent work has shown that recurrent neural networks (RNNs) can implicitly capture and exploit hierarchical information when trained to solve common natural language processing tasks such as language modeling (Linzen et al., 2016) and neural machine translation (Shi et al., 2016).
Examining the Tip of the Iceberg: A Data Set for Idiom Translation
Neural Machine Translation (NMT) has been widely used in recent years with significant improvements for many language pairs.
What does Attention in Neural Machine Translation Pay Attention to?
Thus, the question still remains that how attention is similar or different from the traditional alignment.
Dynamic Data Selection for Neural Machine Translation
Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT).
Learning Topic-Sensitive Word Representations
Distributed word representations are widely used for modeling words in NLP tasks.
Data Augmentation for Low-Resource Neural Machine Translation
The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora.
A Simple but Effective Approach to Improve Arabizi-to-English Statistical Machine Translation
A major challenge for statistical machine translation (SMT) of Arabic-to-English user-generated text is the prevalence of text written in Arabizi, or Romanized Arabic.
Ensemble Learning for Multi-Source Neural Machine Translation
We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i. e., multi-source ensembles, a method recently introduced by Firat et al. (2016).
Measuring the Effect of Conversational Aspects on Machine Translation Quality
Finally, we find that male speakers are harder to translate and use more vulgar language than female speakers, and that vulgarity is often not preserved during translation.
Generating captions without looking beyond objects
This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions.
Recurrent Memory Networks for Language Modeling
In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only amplifies the power of RNN but also facilitates our understanding of its internal functioning and allows us to discover underlying patterns in data.
