Antoine Bordes

Question Answering with Subgraph Embeddings

This paper presents a system which learns to answer questions on a broad range of topics from a knowledge base using few hand-crafted features. Our model learns low-dimensional embeddings of words and knowledge base constituents; these representations are used to score natural language questions against candidate answers. Training our system using pairs of questions and structured representations of their answers, and pairs of question paraphrases, yields competitive results on a recent benchmark of the literature.

A semantic matching energy function for learning with multi-relational data

Large-scale relational learning becomes crucial for handling the huge amounts of structured data generated daily in many application domains ranging from computational biology or information retrieval, to natural language processing. In this paper, we present a new neural network architecture designed to embed multi-relational graphs into a flexible continuous vector space in which the original data is kept and enhanced. The network is trained to encode the semantics of these graphs in order to assign high probabilities to plausible components. We empirically show that it reaches competitive performance in link prediction on standard datasets from the literature as well as on data from a real-world knowledge base (WordNet). In addition, we present how our method can be applied to perform word-sense disambiguation in a context of open-text semantic parsing, where the goal is to learn to assign a structured meaning representation to almost any sentence of free text, demonstrating that it can scale up to tens of thousands of nodes and thousands of types of relation.

Solving multiclass support vector machines with LaRank

Optimization algorithms for large margin multiclass recognizers are often too costly to handle ambitious problems with structured outputs and exponential numbers of classes. Optimization algorithms that rely on the full gradient are not effective because, unlike the solution, the gradient is not sparse and is very large. The LaRank algorithm sidesteps this difficulty by relying on a randomized exploration inspired by the perceptron algorithm. We show that this approach is competitive with gradient based optimizers on simple multiclass problems. Furthermore, a single LaRank pass over the training examples delivers test error rates that are nearly as good as those of the final solution.

Key-Value Memory Networks for Directly Reading Documents

Directly reading documents and being able to answer questions from them is an unsolved challenge. To avoid its inherent difficulty, question answering (QA) has been directed towards using Knowledge Bases (KBs) instead, which has proven effective. Unfortunately KBs often suffer from being too restrictive, as the schema cannot support certain types of answers, and too sparse, e.g. Wikipedia contains much more information than Freebase. In this work we introduce a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation. To compare using KBs, information extraction or Wikipedia documents directly in a single framework we construct an analysis tool, WikiMovies, a QA dataset that contains raw text alongside a preprocessed KB, in the domain of movies. Our method reduces the gap between all three settings. It also achieves state-of-the-art results on the existing WikiQA benchmark.

Open Question Answering with Weakly Supervised Embedding Models

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such approaches can be effective but at the cost of either large amounts of human-labeled data or by defining lexicons and grammars tailored by practitioners. In this paper, we instead take the radical approach of learning to map questions to vectorial feature representations. By mapping answers into the same space one can query any knowledge base independent of its schema, without requiring any grammar or lexicon. Our method is trained with a new optimization procedure combining stochastic gradient descent followed by a fine-tuning step using the weak supervision provided by blending automatically and collaboratively generated resources. We empirically demonstrate that our model can capture meaningful signals from its noisy supervision leading to major improvements over paralex, the only existing method able to be trained on similar weakly labeled data.

Supervised Learning of Universal Sentence Representations from Natural Language Inference Data

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.

The huller: a simple and efficient online SVM

We propose a novel online kernel classifier algorithm that converges to the Hard Margin SVM solution. The same update rule is used to both add and remove support vectors from the current classifier. Experiments suggest that this algorithm matches the SVM accuracies after a single pass over the training examples. This algorithm is attractive when one seeks a competitive classifier with large datasets and limited computing resources.

Sequence labelling SVMs trained in one pass

This paper proposes an online solver of the dual formulation of support vector machines for structured output spaces. We apply it to sequence labelling using the exact and greedy inference schemes. In both cases, the per-sequence training time is the same as a perceptron based on the same inference procedure, up to a small multiplicative constant. Comparing the two inference schemes, the greedy version is much faster. It is also amenable to higher order Markov assumptions and performs similarly on test. In comparison to existing algorithms, both versions match the accuracies of batch solvers that use exact inference after a single pass over the training examples.

Reading Wikipedia to Answer Open-Domain Questions

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

Composing Relationships with Translations

Performing link prediction in Knowledge Bases (KBs) with embedding-based models, like with the model TransE (Bordes et al., 2013) which represents relationships as translations in the embedding space, have shown promising results in recent years. Most of these works are focused on modeling single relationships and hence do not take full advantage of the graph structure of KBs. In this paper, we propose an extension of TransE that learns to explicitly model composition of relationships via the addition of their corresponding translation vectors. We show empirically that this allows to improve performance for predicting single relationships as well as compositions of pairs of them.