Related papers: Object-oriented lexical encoding of multiword expr…
Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we…
Hybrid question answering (HybridQA) over the financial report contains both textual and tabular data, and requires the model to select the appropriate evidence for the numerical reasoning task. Existing methods based on encoder-decoder…
Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current DRL approaches often rely on the unrealistic assumption…
Chinese demonstrates high semantic compactness and rich metaphorical expressiveness, enabling limited text to convey dense meanings while increasing the difficulty of generation and verification, particularly in short-form creative natural…
Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…
Speech signal is constituted and contributed by various informative factors, such as linguistic content and speaker characteristic. There have been notable recent studies attempting to factorize speech signal into these individual factors…
Structural measures of graphs, such as treewidth, are central tools in computational complexity resulting in efficient algorithms when exploiting the parameter. It is even known that modern SAT solvers work efficiently on instances of small…
Electroencephalography (EEG) interpretation using multimodal large language models (MLLMs) offers a novel approach for analyzing brain signals. However, the complex nature of brain activity introduces critical challenges: EEG signals…
Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approaches tackle this problem using implicit feature interaction…
Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they have been adopted…
Extreme multi-label text classification (XMTC) is the task of tagging each document with the relevant labels from a very large space of predefined categories. Recently, large pre-trained Transformer models have made significant performance…
Count-based word alignment methods, such as the IBM models or fast-align, struggle on very small parallel corpora. We therefore present an alternative approach based on cross-lingual word embeddings (CLWEs), which are trained on purely…
Hashing has recently sparked a great revolution in cross-modal retrieval because of its low storage cost and high query speed. Recent cross-modal hashing methods often learn unified or equal-length hash codes to represent the multi-modal…
Feature Structures (FSs) are a widespread tool used for decompositional frameworks of Attribute-Value associations. Even though they thrive in simple systems, they lack a way of representing higher-order entities and relations. This is…
Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space, yet the nature of this internal organization remains elusive. In this work, we investigate…
The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions and causes as pairs from documents. We observe that the relative distance distribution of emotions and causes is extremely imbalanced in the typical ECPE dataset.…
Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive exposures, a process known as fast mapping. This word learning capability is believed to be the most…
This paper concerns the development of metatheory for extensible languages. It uses as its starting point a view that programming languages tailored to specific application domains are to be constructed by composing components from an open…
Large Language Models (LLMs) exploit fine-tuning as a technique to adapt to diverse goals, thanks to task-specific training data. Task specificity should go hand in hand with domain orientation, that is, the specialization of an LLM to…
Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…