Abstract: A method and system for training a machine-learning algorithm (MLA), including first and second machine-learning (ML) models to rank digital documents at a digital platform. The method comprises: receiving first historical data of past searches conducted by the given user over a given past period; receiving second historical data, a given portion of the second historical data including data of past searches conducted by the given user over a given past user session; jointly training both the first and second ML models to rank the in-use digital documents, the training comprising: training, based on the first historical data, the first ML model to generate a vector representation of the first historical data; and training, based on the vector representation of the first historical data and the second historical data, the second ML model to determine a respective likelihood value of the given user interacting with a given in-use digital document.

Abstract: Method and system for authenticating a candidate user are disclosed. The method includes acquiring, by a second service from a first service, a request for a candidate User-Service Unique Identifier (USUID) associated with the candidate user. The candidate USUID is unique for a candidate user-first service pair. The method includes generating, by the second service, the candidate USUID, and sending a token indicative of the candidate USUID. In response to the candidate USUID matching a target USUID, the first service authenticates the candidate user as a target user without prompting the candidate user to provide additional information.

Abstract: Method and server for performing domain-specific translation of sentences. The method includes generating, by the server, an augmented sequence of input tokens based on an input sentence in the first language and a hint inserted into the input sentence. The method includes iteratively generating, using the NN, a sequence of output tokens based on the augmented sequence of input tokens. The method includes generating a second sentence in the second language using the sequence of output tokens, the second sentence including the domain-specific translation of the given input word.

Abstract: Non-limiting embodiments of the present technology are directed to a method and system for generating a training dataset. The method comprises: accessing data associated with a plurality of assessors executing digital tasks of a first type and digital tasks of a second type; generating, a first ranked list of assessors and a second ranked list of assessors based on their past performance; for a given one of the plurality of assessors: generating, a class score for the common class of digital tasks; acquiring a request for executing a digital task of a third type; ranking, the plurality of assessors based on respective class scores, the given one from the plurality of assessors being one of top ranked ones from the plurality of assessors; transmitting the digital task of the third type to the given one; generating the training data for the MLA based on a response from the given one.

Abstract: Methods and electronic devices for batching requests for processing by a processing unit are disclosed. The method includes acquiring a queue of requests to be processed and executing a current iteration for a given batch of requests including the given request from the queue. During the current iteration, the method includes determining a first cost value of adding a first candidate request from the queue to the given batch, determining a second cost value of adding a second candidate request from the queue to the given batch, and selectively adding a target request amongst the first candidate request and the second candidate request to the given batch. The target request being associated with a lowest one of the first cost value and the second cost value.

Abstract: A method and server for generating modified audio data for a video file are disclosed. The method includes acquiring a sequence of first audio portions, and a sequence of second audio portions in different languages. The method includes generating a plurality of candidate arrangements of the sequence of the second audio portions, where a given candidate arrangement is associated with candidate timestamps in the video file and candidate compression rates for respective ones from the sequence of second audio portions. The method includes selecting a target arrangement for the sequence of the second audio portions from the plurality of candidates. The selection is based on the target arrangement having a minimal penalty score amongst penalty scores associated with the plurality of candidates. The method includes generating at least one modified audio portion for the video file as a translation of the audio data using the target arrangement.

Abstract: A method and server for generating a prediction score by a Machine Learned Algorithm (MLA). The method includes: acquiring route data, generating a plurality of route scores for the plurality of routes based on the route data, acquiring driver data, generating a plurality of driver scores for the plurality of drivers based on the driver data, and for a given route-driver pair: generating by the MLA a given prediction score indicative of a likelihood of the given driver having an accident on the given route within a predetermined amount of time after initiating the given route. The method also includes assigning, by employing a dispatching algorithm based on the prediction score, the given route to the given driver for providing a transportation service to the user.

Abstract: There is provided a delivery unit for a cleaning system and a method of operation. The delivery unit has a liquid nozzle for delivering a liquid jet and directing the liquid jet towards a surface of a sensor system, an air nozzle for delivering an air jet and directing the air jet towards the surface of the sensor system, and a deflection orifice for delivering an other air jet for deflecting the liquid jet away from the air nozzle. The liquid nozzle is located proximate to the air nozzle. The air nozzle and the deflection orifice are in fluid communication with a single air manifold.

Abstract: A method and an electronic device for switching play between a first video content and a second video content in a web page of a browser application are provided. The method comprises: acquiring a digital document representative of the web page containing a video tag referencing a first source; establishing a first connection between a first video player and the video tag; playing, by the first video player, the first video content from the first source; in response to a trigger event: pausing the playing of the first video content; and establishing a second connection between a second video player and the video tag; playing, by the second video player, the second video content; in response to ending the playing of the second video content: re-establishing the first connection; and resuming the playing of the first video content by the first video player.

Abstract: A method of operating a robotic vehicle is provided. The method includes generating, using a prediction model, first scores, each of the first scores associated with a possible action of the robotic vehicle. The prediction model generates the first scores based, at least in part, on a predicted probability of the robotic vehicle encountering a dynamic object. The method further includes generating, using an analytical model, second scores, each of the second scores associated with a possible action of the robotic vehicle. The analytical model generates the second scores based, at least in part, on the information on the static objects. The method also includes combining the first scores with the second scores to generate combined scores, and selecting an action for the robotic vehicle based, at least in part, on the combined scores. A motion planning module and a robotic vehicle implementing the method are also disclosed.

Abstract: A method and a system for controlling tracking of web-browsing activities of a user in a browser application are provided. The method comprises: receiving, from a given web server, data representative of a web page to be displayed in the browser application; identifying, based on the data, elements of the web page linked to at least one in-use third-party web resource; obtaining in-use data including at least data of past user interactions of the user with the at least one in-use third-party web resource; feeding the in-use data to an MLA to determine a probability value of the user allowing sharing a respective third-party cookie of the at least one in-use third-party web resource therewith while browsing the web page; in response to the probability value being lower than a threshold value, determining that the user is unlikely to allow sharing the respective third-party cookie while browsing the web page.

Abstract: A method of operating a self-driving vehicle is provided. The method includes predicting a trajectory of an agent in a vicinity of the self-driving vehicle. This is done by: receiving sensor data indicative of a current situation in the vicinity of the self-driving vehicle; generating a current situation feature vector based, at least in part, on the sensor data; searching a pre-built bank of library feature vectors to identify a result feature vector from the pre-built bank that is most relevant to the current situation feature vector, wherein each library feature vector in the pre-built bank is associated with an observed trajectory; and predicting the trajectory of the agent based, at least in part, on the result feature vector. The method also includes planning an action of the vehicle based, at least in part, on the predicted agent trajectory, and operating the vehicle according to the planned action.

Abstract: There is disclosed a method and system for generating a training set for training a machine learning algorithm (MLA) implemented in an information retrieval system. The method is executable by the server and comprises: retrieving, from a search log database of the server, a first query previously submitted to the server, a first SERP associated with the first query, a second query different from the first query and submitted after the first query, and a second SERP associated with the second query, the first query and the second query having been submitted by the electronic device: the first SERP including a first set of search results; and the second SERP including a second set of search results; in response to the second query being submitted within a same search session as the first query, generating the training set to be used as negative training examples for training the MLA.

Abstract: A LIDAR system including an emitter configured to emit at least one light beam; a detector configured for receiving light reflected from surrounding objects; and a rotatable scanning element including a reflective prism having at least four faces inclined relative to the axis of rotation, and a transmission element connected to the reflective prism, the transmission element having an exterior edge portion extending around the axis of rotation generally in a plane orthogonal to the axis of rotation, the edge portion having a variable thickness about the axis of rotation, the emitter, the detector, and the rotatable scanning element being arranged such that the light beam is incident on and refracted by the transmission element and subsequently incident on one face of the at least four faces of the reflective prism, an angle of incidence of the beam on the face depending on the variable thickness of the transmission element.

Abstract: Method and server for determining a target combination of metric-specific thresholds to be used with a plurality of nested metrics for performing binary classification of a digital object are disclosed. The method includes acquiring object-specific validation datasets, and a plurality of nested metrics thereon, thereby generating a plurality of prediction values. During a first iteration, the server compares predictions values against a first combination of metric-specific thresholds and generates first precision parameters and first recall parameters for the first iteration. During a second iteration, the server adjusts one of the first combination thereby generating a second combination, compares the predictions values against the second combination, and generates second precision parameters and second recall parameters for the second iteration. The method includes selecting, by the one of the first combination and the second combination as the target combination of metric-specific thresholds.

Abstract: A method for training a machine learning algorithm for predicting an intent parameter of an object in proximity to a self-driving vehicle on a terrain are provided. The method includes generating a training dataset having assessor-less labels, based on data collected by a training vehicle. The data collected by the training vehicle include data on the state of the training vehicle, the state of a training object, and a training terrain at a target moment in time and at a time after the target moment in time. The training data is based, at least in part, on the data for the target moment in time, and the assessor-less label is based, at least in part, on the data for a time after the target moment in time. A method for operating a self-driving vehicle and a self-driving vehicle are also disclosed.

Abstract: Methods and servers for of training a decision-tree based Machine Learning Algorithm (MLA) are disclosed. During a given training iteration, the method includes generating prediction values using current generated trees, generating estimated gradient values by applying a loss function, generating a first plurality of noisy estimated gradient values based on the estimated gradient values, generating a plurality of noisy candidate trees using the first plurality of noisy estimated gradient values, applying a selection metric to select a target tree amongst the plurality of noisy candidate trees, generating a second plurality of noisy estimated gradient values based on the plurality of estimated gradient values, generating an iteration-specific tree based on the target tree and the second plurality of noisy estimated gradient values, and storing, the iteration-specific tree to be used in combination with the current generated trees.

Abstract: A method and a server for generating textual representations of a user utterance are provided. The method comprises: acquiring an audio signal being an audio representation of the user utterance, the user utterance being in response to a given machine-generated utterance previously outputted by the electronic device to the user; acquiring a machine-generated text string being a textual representation of the given machine-generated utterance; generating, using a Speech-to-Text (STT) model, an other text string based on the audio signal and the machine-generated text string, the other text string being a textual representation of the user utterance while taking into account the machine-generated text string as a context of the user utterance.

Abstract: Method of operating a lid of a robotic vehicle. The lid is operable by a motor between an opened and a closed positions. When the lid is between the opened position and a first intermediary position, a first electric current having a first value is provided to the motor for exerting a first force on the lid. When the lid is between the first intermediary position and a second intermediary position, a second electric current, having a second value whose sign is opposite to a sign of the first value, is provided to the motor for exerting a second force on the lid. The second force is applied in an opposite direction of the first force. When the lid is between the second intermediary position and the closed position, a third electric current having a third value having a same sign than the first value is provided to the motor.