Abstract:In this work, we propose a novel method to incorporate corpus-level discourse information into language modelling. We call this larger-context language model. We introduce a late fusion approach to a recurrent language model based on long shortterm memory units (LSTM), which helps the LSTM unit keep intra-sentence dependencies and inter-sentence dependencies separate from each other. Through the evaluation on four corpora (IMDB, BBC, Penn TreeBank, and Fil9), we demonstrate that the proposed model improves per… Show more
“…Comparison to Exploiting Auxiliary Contexts in Language Modeling: A thread of work in language modeling (LM) attempts to exploit auxiliary sentence-level or document-level context in an RNN LM (Mikolov and Zweig, 2012;Ji et al, 2015;Wang and Cho, 2016). Independent of our work, Wang and Cho (2016) propose "early fusion" models of RNNs where additional information from an intersentence context is "fused" with the input to the RNN.…”
Section: Related Workmentioning
confidence: 99%
“…Comparison to Exploiting Auxiliary Contexts in Language Modeling: A thread of work in language modeling (LM) attempts to exploit auxiliary sentence-level or document-level context in an RNN LM (Mikolov and Zweig, 2012;Ji et al, 2015;Wang and Cho, 2016). Independent of our work, Wang and Cho (2016) propose "early fusion" models of RNNs where additional information from an intersentence context is "fused" with the input to the RNN. Closely related to Wang and Cho (2016), our approach aims to dynamically control the contributions of required source and target contexts for machine translation, while theirs focuses on integrating auxiliary corpus-level contexts for language modelling to better approximate the corpus-level probability.…”
In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Due to the lack of effective control over the influence from source and target contexts, conventional NMT tends to yield fluent but inadequate translations. To address this problem, we propose context gates which dynamically control the ratios at which source and target contexts contribute to the generation of target words. In this way, we can enhance both the adequacy and fluency of NMT with more careful control of the information flow from contexts. Experiments show that our approach significantly improves upon a standard attentionbased NMT system by +2.3 BLEU points.
“…Comparison to Exploiting Auxiliary Contexts in Language Modeling: A thread of work in language modeling (LM) attempts to exploit auxiliary sentence-level or document-level context in an RNN LM (Mikolov and Zweig, 2012;Ji et al, 2015;Wang and Cho, 2016). Independent of our work, Wang and Cho (2016) propose "early fusion" models of RNNs where additional information from an intersentence context is "fused" with the input to the RNN.…”
Section: Related Workmentioning
confidence: 99%
“…Comparison to Exploiting Auxiliary Contexts in Language Modeling: A thread of work in language modeling (LM) attempts to exploit auxiliary sentence-level or document-level context in an RNN LM (Mikolov and Zweig, 2012;Ji et al, 2015;Wang and Cho, 2016). Independent of our work, Wang and Cho (2016) propose "early fusion" models of RNNs where additional information from an intersentence context is "fused" with the input to the RNN. Closely related to Wang and Cho (2016), our approach aims to dynamically control the contributions of required source and target contexts for machine translation, while theirs focuses on integrating auxiliary corpus-level contexts for language modelling to better approximate the corpus-level probability.…”
In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Due to the lack of effective control over the influence from source and target contexts, conventional NMT tends to yield fluent but inadequate translations. To address this problem, we propose context gates which dynamically control the ratios at which source and target contexts contribute to the generation of target words. In this way, we can enhance both the adequacy and fluency of NMT with more careful control of the information flow from contexts. Experiments show that our approach significantly improves upon a standard attentionbased NMT system by +2.3 BLEU points.
“…A larger context language model that incorporates context from preceding sentences (Wang and Cho, 2016), by treating the preceding sentence as a bag of words, and using an attentional mechanism when predicting the next word. An additional hyper-parameter in lclm is the number of preceeding sentences to incorporate, which we tune based on a development set (to 4 sentences in each case).…”
Language models are typically applied at the sentence level, without access to the broader document context. We present a neural language model that incorporates document context in the form of a topic model-like architecture, thus providing a succinct representation of the broader document context outside of the current sentence. Experiments over a range of datasets demonstrate that our model outperforms a pure sentence-based model in terms of language model perplexity, and leads to topics that are potentially more coherent than those produced by a standard LDA topic model. Our model also has the ability to generate related sentences for a topic, providing another way to interpret topics.
“…Finally, we use late fusion (Wang and Cho, 2015) to combine the output of the attention mechanism with the current position in the B-RNN without interfering with its memory.…”
In clinical dictation, speakers try to be as concise as possible to save time, often resulting in utterances without explicit punctuation commands. Since the end product of a dictated report, e.g. an out-patient letter, does require correct orthography, including exact punctuation, the latter need to be restored, preferably by automated means. This paper describes a method for punctuation restoration based on a stateof-the-art stack of NLP and machine learning techniques including B-RNNs with an attention mechanism and late fusion, as well as a feature extraction technique tailored to the processing of medical terminology using a novel vocabulary reduction model. To the best of our knowledge, the resulting performance is superior to that reported in prior art on similar tasks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.