Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links. Text-based methods such as KGBERT (Yao et al., 2019) learn entity representations from natural language descriptions, and have the potential for inductive KGC. However, the performance of text-based methods still largely lag behind graph embedding-based methods like TransE (Bordes et al., 2013) and RotatE (Sun et al., 2019b). In this paper, we identify that the key issue is efficient contrastive learning. To improve the learning efficiency, we introduce three types of negatives: in-batch negatives, pre-batch negatives, and self-negatives which act as a simple form of hard negatives. Combined with InfoNCE loss, our proposed model SimKGC can substantially outperform embedding-based methods on several benchmark datasets. In terms of mean reciprocal rank (MRR), we advance the state-of-the-art by +19% on WN18RR, +6.8% on the Wikidata5M transductive setting, and +22% on the Wikidata5M inductive setting. Thorough analyses are conducted to gain insights into each component. Our code is available at https://github.com/intfloat/SimKGC .

Motivated by the widespread interest in the cross-lingual transfer of NLP models from high resource to low resource languages, research on Cross-lingual word embeddings (CLWEs) has gained much popularity over the years. Among the most successful and attractive CLWE models are the unsupervised CLWE models. These unsupervised CLWE models pose the alignment task as a Wasserstein-Procrustes problem aiming to estimate a permutation matrix and an orthogonal matrix jointly. Most existing unsupervised CLWE models resort to Optimal Transport (OT) based methods to estimate the permutation matrix. However, linear programming algorithms and approximate OT solvers via Sinkhorn for computing the permutation matrix scale cubically and quadratically, respectively, in the input size. This makes it impractical and infeasible to compute OT distances exactly for larger sample size, resulting in a poor approximation quality of the permutation matrix and subsequently a less robust learned transfer function or mapper. This paper proposes an unsupervised projection-based CLWE model called quantized Wasserstein Procrustes (qWP) that jointly estimates a permutation matrix and an orthogonal matrix. qWP relies on a quantization step to estimate the permutation matrix between two probability distributions or measures. This approach substantially improves the approximation quality of empirical OT solvers given fixed computational cost. We demonstrate that qWP achieves state-of-the-art results on the Bilingual lexicon Induction (BLI) task.

Most previous work on temporal relation extraction only focused on extracting the temporal relations among events or suffered from the issue of different expressions of events, timexes and Document Creation Time (DCT). Moreover, DCT can act as a hub to semantically connect the other events and timexes in a document. Unfortunately, previous work cannot benefit from such critical information. To address the above issues, we propose a unified DCT-centered Temporal Relation Extraction model DTRE to identify the relations among events, timexes and DCT. Specifically, sentence-style DCT representation is introduced to address the first issue and unify event expressions, timexes and DCT. Then, a DCT-aware graph is applied to obtain their contextual structural representations. Furthermore, a DCT-anchoring multi-task learning framework is proposed to jointly predict three types of temporal relations in a batch. Finally, we apply a DCT-guided global inference to further enhance the global consistency among different relations. Experimental results on three datasets show that our DTRE outperforms several SOTA baselines on E-E, E-T and E-D significantly.

This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). We propose CREATER, a CTR-driven advertising text generation approach, to generate ad texts based on high-quality user reviews. To incorporate CTR objective, our model learns from online A/B test data with contrastive learning, which encourages the model to generate ad texts that obtain higher CTR. To make use of large-scale unpaired reviews, we design a customized self-supervised objective reducing the gap between pre-training and fine-tuning. Experiments on industrial datasets show that CREATER significantly outperforms current approaches. It has been deployed online in a leading advertising platform and brings uplift on core online metrics.

In this paper, we propose to align sentence representations from different languages into a unified embedding space, where semantic similarities (both cross-lingual and monolingual) can be computed with a simple dot product. Pre-trained language models are fine-tuned with the translation ranking task. Existing work (Feng et al., 2020) uses sentences within the same batch as negatives, which can suffer from the issue of easy negatives. We adapt MoCo (He et al., 2020) to further improve the quality of alignment. As the experimental results show, the sentence representations produced by our model achieve the new state-of-the-art on several tasks, including Tatoeba en-zh similarity search (Artetxe andSchwenk, 2019b), BUCC en-zh bitext mining, and semantic textual similarity on 7 datasets.

Text classification is fundamental in natural language processing (NLP) and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. Therefore in this work, to overcome such problems, we propose TextING for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structure, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are aggregated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods.

We propose to learn distributed sentence representation using text’s visual features as input. Different from the existing methods that render the words or characters of a sentence into images separately, we further fold these images into a 3-dimensional sentence tensor. Then, multiple 3-dimensional convolutions with different lengths (the third dimension) are applied to the sentence tensor, which act as bi-gram, tri-gram, quad-gram, and even five-gram detectors jointly. Similar to the Bi-LSTM, these n-gram detectors learn both forward and backward distributional semantic knowledge from the sentence tensor. That is, the proposed model using bi-directional convolutions to learn text embedding according to the semantic order of words. The feature maps from the two directions are concatenated for final sentence embedding learning. Our model involves only a single-layer of convolution which makes it easy and fast to train. Finally, we evaluate the sentence embeddings on several downstream Natural Language Processing (NLP) tasks, which demonstrate a surprisingly excellent performance of the proposed model.

This paper presents a new sequence-to-sequence (seq2seq) pre-training method PoDA (Pre-training of Denoising Autoencoders), which learns representations suitable for text generation tasks. Unlike encoder-only (e.g., BERT) or decoder-only (e.g., OpenAI GPT) pre-training approaches, PoDA jointly pre-trains both the encoder and decoder by denoising the noise-corrupted text, and it also has the advantage of keeping the network architecture unchanged in the subsequent fine-tuning stage. Meanwhile, we design a hybrid model of Transformer and pointer-generator networks as the backbone architecture for PoDA. We conduct experiments on two text generation tasks: abstractive summarization, and grammatical error correction. Results on four datasets show that PoDA can improve model performance over strong baselines without using any task-specific techniques and significantly speed up convergence.

Neural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task. In this paper, we propose a copy-augmented architecture for the GEC task by copying the unchanged words from the source sentence to the target sentence. Since the GEC suffers from not having enough labeled training data to achieve high accuracy. We pre-train the copy-augmented architecture with a denoising auto-encoder using the unlabeled One Billion Benchmark and make comparisons between the fully pre-trained model and a partially pre-trained model. It is the first time copying words from the source context and fully pre-training a sequence to sequence model are experimented on the GEC task. Moreover, We add token-level and sentence-level multi-task learning for the GEC task. The evaluation results on the CoNLL-2014 test set show that our approach outperforms all recently published state-of-the-art results by a large margin.

Cloze-style reading comprehension has been a popular task for measuring the progress of natural language understanding in recent years. In this paper, we design a novel multi-perspective framework, which can be seen as the joint training of heterogeneous experts and aggregate context information from different perspectives. Each perspective is modeled by a simple aggregation module. The outputs of multiple aggregation modules are fed into a one-timestep pointer network to get the final answer. At the same time, to tackle the problem of insufficient labeled data, we propose an efficient sampling mechanism to automatically generate more training examples by matching the distribution of candidates between labeled and unlabeled data. We conduct our experiments on a recently released cloze-test dataset CLOTH (Xie et al., 2017), which consists of nearly 100k questions designed by professional teachers. Results show that our method achieves new state-of-the-art performance over previous strong baselines.

This paper describes our system for SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. We use Three-way Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment the input with relation embedding from the graph of general knowledge ConceptNet. As a result, our system achieves state-of-the-art performance with 83.95% accuracy on the official test data. Code is publicly available at https://github.com/intfloat/commonsense-rc.

This paper presents a system that participated in SemEval 2017 Task 10 (subtask A and subtask B): Extracting Keyphrases and Relations from Scientific Publications (Augenstein et al., 2017). Our proposed approach utilizes external knowledge to enrich feature representation of candidate keyphrase, including Wikipedia, IEEE taxonomy and pre-trained word embeddings etc. Ensemble of unsupervised models, random forest and linear models are used for candidate keyphrase ranking and keyphrase type classification. Our system achieves the 3rd place in subtask A and 4th place in subtask B.

Topic segmentation plays an important role for discourse parsing and information retrieval. Due to the absence of training data, previous work mainly adopts unsupervised methods to rank semantic coherence between paragraphs for topic segmentation. In this paper, we present an intuitive and simple idea to automatically create a “quasi” training dataset, which includes a large amount of text pairs from the same or different documents with different semantic coherence. With the training corpus, we design a symmetric CNN neural network to model text pairs and rank the semantic coherence within the learning to rank framework. Experiments show that our algorithm is able to achieve competitive performance over strong baselines on several real-world datasets.