Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all lang
uages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pretrained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc finetuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems.
Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle
relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.
Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their cover
age by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN). Specifically, HyperExpan leverages position embeddings to exploit the structure of the existing taxonomies, and characterizes the concept profile information to support the inference on new concepts that are unseen during training. Experiments show that our proposed HyperExpan outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.
Recent metaphor identification approaches mainly consider the contextual text features within a sentence or introduce external linguistic features to the model. But they usually ignore the extra information that the data can provide, such as the cont
extual metaphor information and broader discourse information. In this paper, we propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level. At the sentence level, we leverage the metaphor information of words that except the target word in the sentence to strengthen the reasoning ability of our model via a novel label-enhanced contextualized representation. At the discourse level, the position-aware global memory network is adopted to learn long-range dependency among the same words within a discourse. Finally, our model combines the representations obtained from these two parts. The experiment results on two tasks of the VUA dataset show that our model outperforms every other state-of-the-art method that also does not use any external knowledge except what the pre-trained language model contains.
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-tra
ined acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic representation learning method to fuse and utilize the contextual information of speech and text. Specifically, we unify a pre-trained acoustic model (wav2vec 2.0) and a language model (BERT) into an end-to-end trainable framework. A Representation Aggregation Module is designed to aggregate acoustic and linguistic representation, and an Embedding Attention Module is introduced to incorporate acoustic information into BERT, which can effectively facilitate the cooperation of two pre-trained models and thus boost the representation learning. Extensive experiments show that our Wav-BERT significantly outperforms the existing approaches and achieves state-of-the-art performance on low-resource speech recognition.
Similarity measures are a vital tool for understanding how language models represent and process language. Standard representational similarity measures such as cosine similarity and Euclidean distance have been successfully used in static word embed
ding models to understand how words cluster in semantic space. Recently, these measures have been applied to embeddings from contextualized models such as BERT and GPT-2. In this work, we call into question the informativity of such measures for contextualized language models. We find that a small number of rogue dimensions, often just 1-3, dominate these measures. Moreover, we find a striking mismatch between the dimensions that dominate similarity measures and those which are important to the behavior of the model. We show that simple postprocessing techniques such as standardization are able to correct for rogue dimensions and reveal underlying representational quality. We argue that accounting for rogue dimensions is essential for any similarity-based analysis of contextual language models.
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems. Although various knowledge-grounded conversation models have been proposed, these models have limitations in utilizing knowledge t
hat infrequently occurs in the training data, not to mention integrating unseen knowledge into conversation generation. In this paper, we propose an Entity-Agnostic Representation Learning (EARL) method to introduce knowledge graphs to informative conversation generation. Unlike traditional approaches that parameterize the specific representation for each entity, EARL utilizes the context of conversations and the relational structure of knowledge graphs to learn the category representation for entities, which is generalized to incorporating unseen entities in knowledge graphs into conversation generation. Automatic and manual evaluations demonstrate that our model can generate more informative, coherent, and natural responses than baseline models.
Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low-resource ones. However, due to significant typological differences and
contradictions between some languages, such models usually perform poorly on many languages and cross-lingual settings, which shows the difficulty of learning a single model to handle massive diverse languages well at the same time. To alleviate this issue, we present a new multilingual pre-training pipeline. We propose to generate language representation from multilingual pre-trained model and conduct linguistic analysis to show that language representation similarity reflects linguistic similarity from multiple perspectives, including language family, geographical sprachbund, lexicostatistics, and syntax. Then we cluster all the target languages into multiple groups and name each group as a representation sprachbund. Thus, languages in the same representation sprachbund are supposed to boost each other in both pre-training and fine-tuning as they share rich linguistic similarity. We pre-train one multilingual model for each representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
We propose a method to distill a language-agnostic meaning embedding from a multilingual sentence encoder. By removing language-specific information from the original embedding, we retrieve an embedding that fully represents the sentence's meaning. T
he proposed method relies only on parallel corpora without any human annotations. Our meaning embedding allows efficient cross-lingual sentence similarity estimation by simple cosine similarity calculation. Experimental results on both quality estimation of machine translation and cross-lingual semantic textual similarity tasks reveal that our method consistently outperforms the strong baselines using the original multilingual embedding. Our method consistently improves the performance of any pre-trained multilingual sentence encoder, even in low-resource language pairs where only tens of thousands of parallel sentence pairs are available.
Uric acid (UA) has a role in pathogenesis of several metabolic abnormalities including insulin resistance (IR) and their related disorders. The aim of this report is to review the available evidences that reveal the association between UA, IR and rel
ated disorders via both noninsulin and insulin-based IR indices.
METHODS: The published literature was surveyed using Google Scholar and PubMed entering the terms Obesity, UA, IR, Metabolic Syndrome (MetS), Gestational Diabetes (GDM), Polycystic Ovarian Syndrome (PCOS).
RESULTS: UA had substantial positive relationships with IR, as well as obesity, MetS, DM, GDM, and PCOS. Evidently UA with a role in oxidative stress, endothelial dysfunction and induction of inflammation may cause IR in totality, the major factor in development of MetS and related diseases. Homeostatic Model Assessment of Insulin Resistance (HOMA-IR), insulin based IR index, correlated positively with UA. Moreover, specifically triglyceride to high density lipoprotein cholesterol ratio (TG/HDL-C), visceral adiposity index (VAI), lipid accumulation product (LAP), triglyceride to fasting glucose (TyG) index are noninsulin-based IR indices of positive correlations with UA. MetS score for IR (MetS-IR), a non-insulin based IR index, had significantly proportional correlations with MetS components as well as UA level. UA to HDL-cholesterol ratio (UHR) was a pronounced statistical predictor of MetS and diabetes control. UA positively associated with hyperinsulinemia and IR in prediabetes.
CONCLUSION: Succinctly UA can be an emerging biochemistry marker of predictive role in IR, MetS and related anomalies. More hyperuricemia related studies are warranted to be oriented from being correlational to mechanistic
