Spain

Lexical semantics and world knowledge are crucial for interpreting
bridging anaphora. Yet, existing computational methods for acquiring
and injecting this type of information into bridging resolution
systems suffer important limitations. Based on explicit querying
of external knowledge bases, earlier approaches are computationally
expensive (hence, hardly scalable) and they map the data to be processed
into high-dimensional spaces (careful handling of the curse of 
dimensionality and overfitting has to be in order). In this work, 
we take a different and principled approach which naturally addresses
these issues. Specifically, we convert the external knowledge source (in
this case, WordNet) into a graph, and learn embeddings of the graph
nodes of low dimension to capture the crucial features of the graph topology and, at the same time, rich semantic information. Once properly identified from the mention text spans, these low dimensional graph node embeddings are combined with distributional text-based embeddings to provide 
enhanced mention representations. We illustrate the effectiveness of
our approach by evaluating it on commonly used datasets, namely ISNotes
and BASHI. Our enhanced mention representations yield
significant accuracy improvements on both datasets when compared to
different standalone text-based mention representations.

COLING 2020

Integrating knowledge graph embeddings to improve mention representation for bridging anaphora resolution

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

Shell nouns (SNs) are abstract nouns like fact, issue, and decision, which are capable of referring to non-nominal antecedents, much like anaphoric pronouns. The talk takes a look at a special use case of certain nouns like "issue" and "decision" that seem to be prone to refer to globally available discourse topics instead of local antecedents, which has important implications for the treatment of SNs as a whole in theoretical and automatic approaches.

Reference to Discourse Topics: Introducing “Global” Shell Nouns

Learning to detect entity mentions without us- ing syntactic information can be useful for integration and joint optimization with other tasks. However, it is common to have par- tially annotated data for this problem. Here, we investigate two approaches to deal with partial annotation of mentions: weighted loss and soft-target classification. We also propose two neural mention detection approaches: a sequence tagging, and an exhaustive search. We evaluate our methods with coreference res- olution as a downstream task, using multitask learning. The results show that the recall and F1 score improve for all methods.

Partially-supervised Mention Detection

No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Björkelund and Kuhn, 2014). In this paper, we introduce a coreference resolution system for Arabic based on Lee et al’s end-to-end architecture combined with the Arabic version of bert and an external mention detector. As far as we know, this is the first neural coreference resolution system aimed specifically to Arabic, and it substantially outperforms the existing state-of-the-art on OntoNotes 5.0 with a gain of 15.2 points conll F1.
We also discuss the current limitations of the task for Arabic and possible approaches that can tackle these challenges.

Neural Coreference Resolution for Arabic

In this paper we describe our attempt to increase the amount of information that can be retrievedthrough active learning sessions compared to previous approaches. We optimise the annotator’slabelling process using active learning in the context of coreference resolution. Using simulatedactive learning experiments, we suggest three adjustments to ensure the labelling time is spentas efficiently as possible. All three adjustments provide more information to the machine learnerthan the baseline, though a large impact on the F1 score over time is not observed. Compared toprevious models, we report a marginal F1 improvement on the final coreference models trainedusing for two out of the three approaches tested when applied to the English OntoNotes 2012Coreference Resolution data. Our best-performing model achieves 58.01 F1, an increase of 0.93F1 over the baseline model.

Enhanced Labelling in Active Learning for Coreference Resolution

Many people live-tweet televised events like Presidential debates and popular TV-shows and discuss people or characters in the event. Naturally, many tweets make pronominal reference to these people/characters. We propose an algorithm for resolving personal pronouns that make reference to people involved in an event, in tweet streams collected during the event.

Resolving Pronouns in Twitter Streams: Context can Help!

We present a study focusing on variation of coreferential devices in English original TED talks and news texts and their German translations. Using exploratory techniques we contemplate a diverse set of coreference devices as features which we assume indicate language-specific and register-based variation as well as potential translation strategies. Our findings reflect differences on both dimensions with stronger variation along the lines of register than between languages. By exposing interactions between text type and cross-linguistic variation, they can also inform multilingual NLP applications, especially machine translation.

Coreference Strategies in English-German Translation

We introduce the IMS contribution to the Surface Realization Shared Task 2020. Our current system achieves substantial improvement over the state-of-the-art system from last year, mainly due to a better token representation and a better linearizer, as well as a simple ensembling approach. We also experiment with data augmentation, which brings some additional performance gain. The system is available at \url{https://github.com/EggplantElf/IMSurReal}.

IMSurReal Too: IMS at the Surface Realization Shared Task 2020

We present a system for mapping Universal Dependency structures to raw text which learns to
restore word order by training an Interpreted Regular Tree Grammar (IRTG) that establishes
a mapping between string and graph operations. The reinflection step is handled by a standard
sequence-to-sequence architecture with a biLSTM encoder and an LSTM decoder with attention.
We modify our 2019 system (Kovács et al., 2019) with a new grammar induction mechanism
that allows IRTG rules to operate on lemmata in addition to part-of-speech tags and ensures that
each word and its dependents are reordered using the most specific set of learned patterns. We
also introduce a hierarchical approach to word order restoration that independently determines
the word order of each clause in a sentence before arranging them with respect to the main
clause, thereby improving overall readability and also making the IRTG parsing task tractable.
We participated in the 2020 Surface Realization Shared task, subtrack T1a (shallow, closed).
Human evaluation shows we achieve significant improvements on two of the three out-of-domain
datasets compared to the 2019 system we modified. Both components of our system are available
on GitHub under an MIT license.

BME-TUW at SR’20: Lexical grammar induction for surface realization

This paper describes the submission by the NILC Computational Linguistics research group of the University of São Paulo/Brazil to the English Track 2 (closed sub-track) at the Surface Realisation Shared Task 2020. The success of the current pre-trained models like BERT or GPT-2 in several tasks is well-known, however, this is not the case for data-to-text generation tasks and just recently some initiatives focused on it. This way, we explore how a pre-trained model (GPT-2) performs on the UD-to-text generation task. In general, the achieved results were poor, but there are some interesting ideas to explore. Among the learned lessons we may note that it is necessary to study strategies to represent UD inputs and to introduce structural knowledge into these pre-trained models.

NILC at SR'20: Exploring Pre-Trained Models in Surface Realisation

In the context of Natural Language Generation, surface realization is the task of generating the linear form of a text following a given grammar. Surface realization models usually consist of a cascade of complex sub-modules, either rule-based or neural network-based, each responsible for a specific sub-task. In this work, we show that a single encoder-decoder language model can be used in an end-to-end fashion for all sub-tasks of surface realization. The model is designed based on the BART language model that receives a linear representation of unordered and non-inflected tokens in a sentence along with their corresponding Universal Dependency information and produces the linear sequence of inflected tokens along with the missing words. The model was evaluated on the shallow and deep tracks of the 2020 Surface Realization Shared Task (SR'20) using both human and automatic evaluation. The results indicate that despite its simplicity, our model achieves competitive results among all participants in the shared task.

Downloads

Next from COLING 2020

Reference to Discourse Topics: Introducing “Global” Shell Nouns

Similar lecture

Reference to Discourse Topics: Introducing “Global” Shell Nouns

.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

Reference to Discourse Topics: Introducing “Global” Shell Nouns

Similar lecture

Reference to Discourse Topics: Introducing “Global” Shell Nouns

Downloads