Spain

Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this paper, we conduct an investigation into pure character-based models in the case of translating Finnish into English, including exploring the ability to learn word senses and morphological inflections and the attention mechanism. We demonstrate that word-level information is distributed over the entire character sequence rather than over a single character, and characters at different positions play different roles in learning linguistic knowledge. In addition, character-based models need more layers to encode word senses which explains why only deeper models outperform subword-based models. The attention distribution pattern shows that separators attract a lot of attention and we explore a sparse word-level attention to enforce character hidden states to capture the full word-level information. Experimental results show that the word-level attention with a single head results in 1.2 BLEU points drop.

COLING 2020

Understanding Pure Character-Based NMT Models

character-based

linguistic knowledge

attention mechanisms

probing

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

poster

Deep neural models tremendously improved machine translation. In this context, we investigate whether distinguishing machine from human translations is still feasible. We trained and applied 18 classifiers under two settings: a monolingual task, in which the classifier only looks at the (French) translation; and a bilingual task, in which the source text (in English) is also taken into consideration. We report on extensive experiments involving 4 neural MT systems (Google Translate, DeepL, as well as two systems we trained) and varying the domain of texts. We show that the bilingual task is the easiest one and that transfer-based deep-learning classifiers perform best, with mean accuracies around 85% in-domain and 75% out-of-domain.

Human or Neural Translation?

Neural Machine Translation often suffers from over- and under-translation problems due to its limited modeling of output sequence lengths. In this work, we propose a novel approach to training a Transformer model using length constraints based on a length-aware positional encoding (PE). Since the length constraints with exact target sentence lengths cause some degradation in translation performance, we add random noise within a certain window size to the length constraints in the PE during the training. In inference, we predict output lengths using input sequences and a BERT-based length prediction model. Experimental results in ASPEC English-to-Japanese translation showed the proposed method gave translations close to reference lengths and outperformed a vanilla Transformer especially in short sentences, by 2.42 points in BLEU. Also, translation results using our length prediction model was better in average than another baseline method using input lengths for the length constraints. The proposed noise injection improved robustness for length prediction errors especially within the window size.

Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings

Graph-based meaning representations (MRs) exhibit structural differences that reflect different theoretical and design considerations, presenting challenges to uniform linguistic analysis and cross-framework semantic parsing. Here, we ask the question of which design differences between MRs are meaningful and semantically-rooted, and which are superficial. We present a methodology for normalizing discrepancies between MRs at the compositional level (Lindemann et al., 2019), finding that we can normalize the majority of divergent phenomena using linguistically-grounded rules. Our work significantly increases the match in compositional structure between MRs and improves multi-task learning (MTL) in a low-resource setting.

Normalizing Compositional Structures Across Graphbanks

Recent work has shown that pre-trained Transformers obtain remarkable performance on many natural language processing tasks, including automatic summarization. However, most work has focused on (relatively) data-rich single-document summarization settings. In this paper, we explore highly-abstractive multi-document summarization, where the summary is explicitly conditioned on a user-given topic statement or question. We compare the summarization quality produced by three state-of-the-art transformer-based models: BART, T5, and PEGASUS. We report the performance on four challenging summarization datasets: three from the general domain and one from consumer health in both zero-shot (ZSL) and few-shot (FSL) learning settings.

Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization

We define a mapping from transition-based parsing algorithms that read sentences from left to right to sequence labeling encodings of syntactic trees. This not only establishes a theoretical relation between transition-based parsing and sequence-labeling parsing, but also provides a method to obtain new encodings for fast and simple sequence labeling parsing from the many existing transition-based parsers for different formalisms. Applying it to dependency parsing, we implement sequence labeling versions of four algorithms, showing that they are learnable and obtain comparable performance to existing encodings.

A Unifying Theory of Transition-Based and Sequence Labeling Parsing

In this work, we carry out two experiments in order to assess the ability of BERT to capture the meaning shift associated with metonymic expressions. We test the model on a new dataset that is representative of the most common types of metonymy. We compare BERT with the Structured Distributional Model (SDM), a model for the representation of words in context which is based on the notion of Generalized Event Knowledge. The results reveal that, while BERT ability to deal with metonymy is quite limited, SDM is good at predicting the meaning of metonymic expressions, providing support for an account of metonymy based on event knowledge.

Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations

However, geographical locations occur not only as individual toponyms, but also as compositions of reference geolocations joined and modified by connectives, e.g., "between the towns of Adrano and S.Maria di Licodia, 32 kilometres northwest of Catania". Ideally, a geoparser should be able to take such text, and the geographical shapes of the toponyms referenced within it, and parse these into a geographical shape, formed by a set of coordinates, that represents the location described. But creating a dataset for this complex geoparsing task is difficult and, if done manually, would require a huge amount of effort to annotate the geographical shapes of not only the geolocation described but also the reference toponyms. We present an approach that automates most of the process by combining Wikipedia and OpenStreetMap. As a result, we have gathered a collection of 360,187 uncurated complex geolocation descriptions, from which we have manually curated 1,000 examples intended to be used as a test set. To accompany the data, we define a new geoparsing evaluation framework along with a scoring methodology and a set of baselines.

A Dataset and Evaluation Framework for Complex Geographical Description Parsi

RST-based discourse parsing is an important NLP task with numerous downstream applications, such as summarization, machine translation and opinion mining. In this paper, we demonstrate a simple, yet highly accurate discourse parser, incorporating recent contextual language models. Our parser establishes the new state-of-the-art (SOTA) performance for predicting structure and nuclearity on two key RST datasets, RST-DT and Instr-DT. We further demonstrate that pretraining our parser on the recently available large-scale ``silver-standard" discourse treebank MEGA-DT provides even larger performance benefits, suggesting a novel and promising research direction in the field of discourse analysis. 


Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining

Data-to-text Natural Language Generation (NLG) is the computational process of generating natural language in the form of text or voice from non-linguistic data. A core micro-planning task within NLG is referring expression generation (REG), which aims to automatically generate noun phrases to refer to entities mentioned as discourse unfolds. A limitation of novel REG models is not being able to generate referring expressions to entities not encountered during the training process. To solve this problem, we propose two extensions to NeuralREG, a state-of-the-art encoder-decoder REG model. The first is a copy mechanism, whereas the second consists of representing the gender and type of the referent as inputs to the model. Drawing on the results of automatic and human evaluation as well as an ablation study using the WebNLG corpus, we contend that our proposal contributes to the generation of more meaningful referring expressions to unseen entities than the original system and related work. Code and all produced data are publicly available

Referring to what you know and do not know: Making Referring Expression Generation Models Generalize To Unseen Entities

Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistic structures. To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data. We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.

Understanding Pure Character-Based NMT Models

Downloads

Next from COLING 2020

Human or Neural Translation?

Similar lecture

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation

Understanding Pure Character-Based NMT Models

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Human or Neural Translation?

Similar lecture

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation

Downloads