In the last few years, several methods have been proposed to build meta-embeddings. The general aim was to obtain new representations integrating complementary knowledge from different source pre-trained embeddings thereby improving their overall qua
lity. However, previous meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach. In this paper we propose a unified common framework, including both intrinsic and extrinsic tasks, for a fair and objective meta-embeddings evaluation. Furthermore, we present a new method to generate meta-embeddings, outperforming previous work on a large number of intrinsic evaluation benchmarks. Our evaluation framework also allows us to conclude that previous extrinsic evaluations of meta-embeddings have been overestimated.
Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces. For contextualized embeddings, alignment becomes more c
omplex as we additionally take context into consideration. In this work, we propose using Optimal Transport (OT) as an alignment objective during fine-tuning to further improve multilingual contextualized representations for downstream cross-lingual transfer. This approach does not require word-alignment pairs prior to fine-tuning that may lead to sub-optimal matching and instead learns the word alignments within context in an unsupervised manner. It also allows different types of mappings due to soft matching between source and target sentences. We benchmark our proposed method on two tasks (XNLI and XQuAD) and achieve improvements over baselines as well as competitive results compared to similar recent works.
Relative position embedding (RPE) is a successful method to explicitly and efficaciously encode position information into Transformer models. In this paper, we investigate the potential problems in Shaw-RPE and XL-RPE, which are the most representati
ve and prevalent RPEs, and propose two novel RPEs called Low-level Fine-grained High-level Coarse-grained (LFHC) RPE and Gaussian Cumulative Distribution Function (GCDF) RPE. LFHC-RPE is an improvement of Shaw-RPE, which enhances the perception ability at medium and long relative positions. GCDF-RPE utilizes the excellent properties of the Gaussian function to amend the prior encoding mechanism in XL-RPE. Experimental results on nine authoritative datasets demonstrate the effectiveness of our methods empirically. Furthermore, GCDF-RPE achieves the best overall performance among five different RPEs.
We propose a new reference-free summary quality evaluation measure, with emphasis on the faithfulness. The measure is based on finding and counting all probable potential inconsistencies of the summary with respect to the source document. The propose
d ESTIME, Estimator of Summary-to-Text Inconsistency by Mismatched Embeddings, correlates with expert scores in summary-level SummEval dataset stronger than other common evaluation measures not only in Consistency but also in Fluency. We also introduce a method of generating subtle factual errors in human summaries. We show that ESTIME is more sensitive to subtle errors than other common evaluation measures.
Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space. However, the necessity of hyperbolic space in KGE is still questionable, because the calculation based on hype
rbolic geometry is much more complicated than Euclidean operations. In this paper, based on the state-of-the-art hyperbolic-based model RotH, we develop two lightweight Euclidean-based models, called RotL and Rot2L. The RotL model simplifies the hyperbolic operations while keeping the flexible normalization effect. Utilizing a novel two-layer stacked transformation and based on RotL, the Rot2L model obtains an improved representation capability, yet costs fewer parameters and calculations than RotH. The experiments on link prediction show that Rot2L achieves the state-of-the-art performance on two widely-used datasets in low-dimensional knowledge graph embeddings. Furthermore, RotL achieves similar performance as RotH but only requires half of the training time.
Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-network for this task, which obtains the sentence embeddings through mo
deling the context-response semantic relevance by applying a feed-forward network on top of the sentence encoders. However, as the semantic textual similarity is commonly measured through the element-wise distance metrics (e.g. cosine and L2 distance), such architecture yields a large gap between training and evaluating. In this paper, we propose DialogueCSE, a dialogue-based contrastive learning approach to tackle this issue. DialogueCSE first introduces a novel matching-guided embedding (MGE) mechanism, which generates a context-aware embedding for each candidate response embedding (i.e. the context-free embedding) according to the guidance of the multi-turn context-response matching matrices. Then it pairs each context-aware embedding with its corresponding context-free embedding and finally minimizes the contrastive loss across all pairs. We evaluate our model on three multi-turn dialogue datasets: the Microsoft Dialogue Corpus, the Jing Dong Dialogue Corpus, and the E-commerce Dialogue Corpus. Evaluation results show that our approach significantly outperforms the baselines across all three datasets in terms of MAP and Spearman's correlation measures, demonstrating its effectiveness. Further quantitative experiments show that our approach achieves better performance when leveraging more dialogue context and remains robust when less training data is provided.
High quality distributional models can capture lexical and semantic relations between words. Hence, researchers design various intrinsic tasks to test whether such relations are captured. However, most of the intrinsic tasks are designed for modern l
anguages, and there is a lack of evaluation methods for distributional models of historical corpora. In this paper, we conducted BAHP: a benchmark of assessing word embeddings in Historical Portuguese, which contains four types of tests: analogy, similarity, outlier detection, and coherence. We examined word2vec models generated from two historical Portuguese corpora in these four test sets. The results demonstrate that our test sets are capable of measuring the quality of vector space models and can provide a holistic view of the model's ability to capture syntactic and semantic information. Furthermore, the methodology for the creation of our test sets can be easily extended to other historical languages.
Growing polarization of the news media has been blamed for fanning disagreement, controversy and even violence. Early identification of polarized topics is thus an urgent matter that can help mitigate conflict. However, accurate measurement of topic-
wise polarization is still an open research challenge. To address this gap, we propose Partisanship-aware Contextualized Topic Embeddings (PaCTE), a method to automatically detect polarized topics from partisan news sources. Specifically, utilizing a language model that has been finetuned on recognizing partisanship of the news articles, we represent the ideology of a news corpus on a topic by corpus-contextualized topic embedding and measure the polarization using cosine distance. We apply our method to a dataset of news articles about the COVID-19 pandemic. Extensive experiments on different news sources and topics demonstrate the efficacy of our method to capture topical polarization, as indicated by its effectiveness of retrieving the most polarized topics.
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising conversation
al query reformulation and information retrieval modules. Despite its effectiveness, such a pipeline often includes multiple neural models that require long inference times. In addition, independently optimizing each module ignores dependencies among them. To address these shortcomings, we propose to integrate conversational query reformulation directly into a dense retrieval model. To aid in this goal, we create a dataset with pseudo-relevance labels for conversational search to overcome the lack of training data and to explore different training strategies. We demonstrate that our model effectively rewrites conversational queries as dense representations in conversational search and open-domain question answering datasets. Finally, after observing that our model learns to adjust the L2 norm of query token embeddings, we leverage this property for hybrid retrieval and to support error analysis.
Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling generation
, e.g., to ensure specific words are included, either require additional models or fine-tuning, or work poorly when the task at hand is semantically unconstrained, e.g., story generation. In this work, we present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sentence: given a topic or keyword, we add a shift to the probability distribution over our vocabulary towards semantically similar words. We show how annealing this distribution can be used to impose hard constraints on language generation, something no other plug-and-play method is currently able to do with SOTA language generators. Despite the simplicity of this approach, we see it works incredibly well in practice: decoding from GPT-2 leads to diverse and fluent sentences while guaranteeing the appearance of given guide words. We perform two user studies, revealing that (1) our method outperforms competing methods in human evaluations; and (2) forcing the guide words to appear in the generated text has no impact on the fluency of the generated text.
