Alert button
Picture for Ran Tian

Ran Tian

Alert button

Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation

Nov 15, 2019
Ran Tian, Shashi Narayan, Thibault Sellam, Ankur P. Parikh

Figure 1 for Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
Figure 2 for Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
Figure 3 for Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
Figure 4 for Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation

Neural conditional text generation systems have achieved significant progress in recent years, showing the ability to produce highly fluent text. However, the inherent lack of controllability in these systems allows them to hallucinate factually incorrect phrases that are unfaithful to the source, making them often unsuitable for many real world systems that require high degrees of precision. In this work, we propose a novel confidence oriented decoder that assigns a confidence score to each target position. This score is learned in training using a variational Bayes objective, and can be leveraged at inference time using a calibration technique to promote more faithful generation. Experiments on a structured data-to-text dataset -- WikiBio -- show that our approach is more faithful to the source than existing state-of-the-art approaches, according to both automatic metrics and human evaluation.

Viaarxiv icon

Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning

Oct 22, 2019
Ran Tian, Nan Li, Ilya Kolmanovsky, Anouck Girard

Figure 1 for Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning
Figure 2 for Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning
Figure 3 for Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning
Figure 4 for Beating humans in a penny-matching game by leveraging cognitive hierarchy theory and Bayesian learning

It is a long-standing goal of artificial intelligence (AI) to be superior to human beings in decision making. Games are suitable for testing AI capabilities of making good decisions in non-numerical tasks. In this paper, we develop a new AI algorithm to play the penny-matching game considered in Shannon's "mind-reading machine" (1953) against human players. In particular, we exploit cognitive hierarchy theory and Bayesian learning techniques to continually evolve a model for predicting human player decisions, and let the AI player make decisions according to the model predictions to pursue the best chance of winning. Experimental results show that our AI algorithm beats 27 out of 30 volunteer human players.

* IEEE 2020 American Control Conference 
Viaarxiv icon

Game-theoretic Modeling of Traffic in Unsignalized Intersection Network for Autonomous Vehicle Control Verification and Validation

Oct 20, 2019
Ran Tian, Nan Li, Ilya Kolmanovsky, Yildiray Yildiz, Anouck Girard

Figure 1 for Game-theoretic Modeling of Traffic in Unsignalized Intersection Network for Autonomous Vehicle Control Verification and Validation
Figure 2 for Game-theoretic Modeling of Traffic in Unsignalized Intersection Network for Autonomous Vehicle Control Verification and Validation
Figure 3 for Game-theoretic Modeling of Traffic in Unsignalized Intersection Network for Autonomous Vehicle Control Verification and Validation
Figure 4 for Game-theoretic Modeling of Traffic in Unsignalized Intersection Network for Autonomous Vehicle Control Verification and Validation

For a foreseeable future, autonomous vehicles (AVs) will operate in traffic together with human-driven vehicles. The AV planning and control systems need extensive testing, including early-stage testing in simulations where the interactions among autonomous/human-driven vehicles are represented. Motivated by the need for such simulation tools, we propose a game-theoretic approach to modeling vehicle interactions, in particular, for urban traffic environments with unsignalized intersections. We develop traffic models with heterogeneous (in terms of their driving styles) and interactive vehicles based on our proposed approach, and use them for virtual testing, evaluation, and calibration of AV control systems. For illustration, we consider two AV control approaches, analyze their characteristics and performance based on the simulation results with our developed traffic models, and optimize the parameters of one of them.

* IEEE Intelligent Transportation Systems Transactions 
Viaarxiv icon

Adaptive Game-Theoretic Decision Making for Autonomous Vehicle Control at Roundabouts

Oct 01, 2018
Ran Tian, Sisi Li, Nan Li, Ilya Kolmanovsky, Anouck Girard, Yildiray Yildiz

Figure 1 for Adaptive Game-Theoretic Decision Making for Autonomous Vehicle Control at Roundabouts
Figure 2 for Adaptive Game-Theoretic Decision Making for Autonomous Vehicle Control at Roundabouts
Figure 3 for Adaptive Game-Theoretic Decision Making for Autonomous Vehicle Control at Roundabouts
Figure 4 for Adaptive Game-Theoretic Decision Making for Autonomous Vehicle Control at Roundabouts

In this paper, we propose a decision making algorithm for autonomous vehicle control at a roundabout intersection. The algorithm is based on a game-theoretic model representing the interactions between the ego vehicle and an opponent vehicle, and adapts to an online estimated driver type of the opponent vehicle. Simulation results are reported.

* 2018 IEEE Conference on Decision and Control (CDC) 
Viaarxiv icon

Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder

May 24, 2018
Ryo Takahashi, Ran Tian, Kentaro Inui

Figure 1 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Figure 2 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Figure 3 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder
Figure 4 for Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder

Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in the parameter space of arbitrary matrices---for one reason, composition of two relations $\boldsymbol{M}_1,\boldsymbol{M}_2$ may match a third $\boldsymbol{M}_3$ (e.g. composition of relations currency_of_country and country_of_film usually matches currency_of_film_budget), which imposes compositional constraints to be satisfied by the parameters (i.e. $\boldsymbol{M}_1\cdot \boldsymbol{M}_2\approx \boldsymbol{M}_3$). In this paper we investigate a dimension reduction technique by training relations jointly with an autoencoder, which is expected to better capture compositional constraints. We achieve state-of-the-art on Knowledge Base Completion tasks with strongly improved Mean Rank, and show that joint training with an autoencoder leads to interpretable sparse codings of relations, helps discovering compositional constraints and benefits from compositional training. Our source code is released at github.com/tianran/glimvec.

* Equal contribution from first two authors. Accepted for publication in the ACL 2018 
Viaarxiv icon

The Mechanism of Additive Composition

Mar 07, 2017
Ran Tian, Naoaki Okazaki, Kentaro Inui

Figure 1 for The Mechanism of Additive Composition
Figure 2 for The Mechanism of Additive Composition
Figure 3 for The Mechanism of Additive Composition
Figure 4 for The Mechanism of Additive Composition

Additive composition (Foltz et al, 1998; Landauer and Dumais, 1997; Mitchell and Lapata, 2010) is a widely used method for computing meanings of phrases, which takes the average of vector representations of the constituent words. In this article, we prove an upper bound for the bias of additive composition, which is the first theoretical analysis on compositional frameworks from a machine learning point of view. The bound is written in terms of collocation strength; we prove that the more exclusively two successive words tend to occur together, the more accurate one can guarantee their additive composition as an approximation to the natural phrase vector. Our proof relies on properties of natural language data that are empirically verified, and can be theoretically derived from an assumption that the data is generated from a Hierarchical Pitman-Yor Process. The theory endorses additive composition as a reasonable operation for calculating meanings of phrases, and suggests ways to improve additive compositionality, including: transforming entries of distributional word vectors by a function that meets a specific condition, constructing a novel type of vector representations to make additive composition sensitive to word order, and utilizing singular value decomposition to train word vectors.

* More explanations on theory and additional experiments added. Accepted by Machine Learning Journal 
Viaarxiv icon

Learning Semantically and Additively Compositional Distributional Representations

Jun 08, 2016
Ran Tian, Naoaki Okazaki, Kentaro Inui

Figure 1 for Learning Semantically and Additively Compositional Distributional Representations
Figure 2 for Learning Semantically and Additively Compositional Distributional Representations
Figure 3 for Learning Semantically and Additively Compositional Distributional Representations
Figure 4 for Learning Semantically and Additively Compositional Distributional Representations

This paper connects a vector-based composition model to a formal semantics, the Dependency-based Compositional Semantics (DCS). We show theoretical evidence that the vector compositions in our model conform to the logic of DCS. Experimentally, we show that vector-based composition brings a strong ability to calculate similar phrases as similar vectors, achieving near state-of-the-art on a wide range of phrase similarity tasks and relation classification; meanwhile, DCS can guide building vectors for structured queries that can be directly executed. We evaluate this utility on sentence completion task and report a new state-of-the-art.

* to appear in ACL2016 
Viaarxiv icon