Spain

BERT is a popular language model whose main pre-training task is to fill in the blank, i.e., predicting a word that was masked out of a sentence, based on the remaining words. In some applications, however, having an additional context can help the model make the right prediction, e.g., by taking the domain or the time of writing into account. This motivates us to advance the BERT architecture by adding a global state for conditioning on a fixed-sized context. We present our two novel approaches and apply them to an industry use-case, where we complete fashion outfits with missing articles, conditioned on a specific customer. An experimental comparison to other methods from the literature shows that our methods improve personalization significantly.

COLING 2020

Contextual BERT: Conditioning the Language Model Using a Global State

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.

technical paper

We propose an open-world knowledge graph completion model that can be combined with common closed-world approaches (such as ComplEx) and enhance them to exploit text-based representations for entities unseen in training. Our model learns relation-specific transformation functions from text-based to graph-based embedding space, where the closed-world link prediction model can be applied. We demonstrate state-of-the-art results on common open-world benchmarks and show that our approach benefits from relation-specific transformation functions (RST), giving substantial improvements over a relation-agnostic approach.

Relation Specific Transformations for Open World Knowledge Graph Completion (TextGraphs #13)

Word Sense Disambiguation (WSD) is a well-known problem in the natural language processing. In recent years, there has been increasing interest in applying neural networks and machine learning techniques to solve WSD problems. However, these previous supervised approaches often suffer from the lack of manually sense-tagged examples. In this paper, to solve these problems, we propose a semi-supervised WSD method using graph embeddings based learning method in order to make effective use of labeled and unlabeled examples. The results of the experiments show that the proposed method performs better than the previous semi-supervised WSD method. Moreover, the graph structure between examples is effective for WSD and it is effective to utilize a graph structure obtained by fine-tuning BERT in the proposed method.

Semi-supervised Word Sense Disambiguation Using Example Similarity Graph

We present a novel method for injecting temporality into entailment graphs to address the problem of spurious entailments, which may arise from similar but temporally distinct events involving the same pair of entities. We focus on the sports domain in which the same pairs of teams play on different occasions, with different outcomes. We present an unsupervised model that aims to learn entailments such as win/lose → play, while avoiding the pitfall of learning non-entailments such as win /→ lose. We evaluate our model on a manually constructed dataset, showing that incorporating time intervals and applying a temporal window around them, are effective strategies.

Incorporating Temporal Information in Entailment Graph Mining

This paper is a system description of HMSid, officially sent to the PARSEME Shared Task 2020 for one language (French), in the open track. It also describes HMSid2, sent to the organizers of the workshop after the deadline and using the same methodology but in the closed track. Both systems do not rely on machine learning, but on computational corpus linguistics. Their score for unseen MWEs is very promising, especially in the case of HMSid2, which would have received the best score for unseen MWEs in the French closed track.

HMSid and HMSid2 at PARSEME Shared Task 2020: Computational Corpus Linguistics and unseen-in-training MWEs


In this work, we present the construction of multilingual parallel corpora with annotation of multiword expressions (MWEs). MWEs include verbal MWEs (vMWEs) defined in the PARSEME shared task that have a verb as the head of the studied terms. The annotated vMWEs are also bilingually and multilingually aligned manually. The languages covered include English, Chinese, Polish, and German. Our original English corpus is taken from the PARSEME shared task in 2018. We performed machine translation of this source corpus followed by human post editing and annotation of target MWEs. Strict quality control was applied for error limitation, i.e., each MT output sentence received first manual post editing and annotation plus second manual quality rechecking. One of our findings during corpora preparation is that accurate translation of MWEs presents challenges to MT systems. To facilitate further MT research, we present a categorisation of the error types encountered by MT systems in performing MWE related translation. To acquire a broader view of MT issues, we selected four popular state-of-the-art MT models for comparisons namely: Microsoft Bing Translator, GoogleMT, Baidu Fanyi and DeepL MT. Because of the noise removal, translation post editing and MWE annotation by human professionals, we believe our AlphaMWE dataset will be an asset for cross-lingual and multilingual research, such as MT and information extraction. Our multilingual corpora are available as open access at github.com/poethan/AlphaMWE

AlphaMWE: Construction of Multilingual Parallel Corpora with MWE Annotations

We describe the Seen2Unseen system that participated in edition 1.2 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs). The identification of VMWEs that do not appear in the provided training corpora (called unseen VMWEs) – with a focus here on verb-noun VMWEs – is based on mutual information and lexical substitution or translation of seen VMWEs. We present the architecture of the system, report results for 14
languages, and propose an error analysis.

All Roads do not Lead to Unseen Verb-Noun VMWEs

When repairing a device, humans employ a series of tools that corresponds to the arrangement of the device components. Such sequences of tool usage can be learned from repair manuals, so that at each step, having observed the previously applied tools, a sequential model can predict the next required tool. In this paper, we improve the tool prediction performance of such methods by additionally taking the hierarchical relationships among the tools into account. To this aim, we build a taxonomy of tools with hyponymy and hypernymy relations from the data by decomposing all multi-word expressions of tool names. We then develop a sequential model that performs a binary prediction for each node in the taxonomy. The evaluation of the method on a dataset of repair manuals shows that encoding the tools with the constructed taxonomy and using a top-down beam search for decoding increases the prediction accuracy and yields an interpretable taxonomy as a potentially valuable byproduct.

Hierarchy-aware Learning of Sequential Tool Usage via Semi-automatically Constructed Taxonomies

We introduce CollFrEn, a language resource focused on collocations for two languages: English and French. We compiled, categorized, enriched and disambiguated thousands of collocations, and we also release corpus samples where they occur, as well as dedicated embedding space.

CollFrEn: Rich Bilingual English--French Collocation Resource

Through comparison with several human-annotated reference sets, we find word2vec to be substantively superior to GloVe for unsupervised measurement
of the semantic compositionality of MWE candidates. We also demonstrate that a sample of 10% of sentences in the English Wikipedia can provide a conveniently tractable corpus with only moderate reduction in the quality of outputs.

Comparing word2vec and GloVe for Automatic Measurement of MWE Compositionality

In this presentation, we explore the categories of VMWEs that exist in Irish, including some of the challenges with annotating these categories. We present the resulting corpora and examine the results of the PARSEME Shared Task for Irish.

Contextual BERT: Conditioning the Language Model Using a Global State

Downloads

Next from COLING 2020

Relation Specific Transformations for Open World Knowledge Graph Completion (TextGraphs #13)

Similar lecture

Domain Transfer based Data Augmentation for Neural Query Translation

Contextual BERT: Conditioning the Language Model Using a Global State

.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

Relation Specific Transformations for Open World Knowledge Graph Completion (TextGraphs #13)

Similar lecture

Domain Transfer based Data Augmentation for Neural Query Translation

Downloads